Awesome MCP

Note: This repository contains an automatically compiled list of frameworks, tools, and resources related to Model Context Protocol (MCP).

A curated list of awesome Model Context Protocol (MCP) and Model Context Protocol-related software.

Table of Contents:

• MCP Servers

  • Databases (39)

  • Cloud & DevOps (35)

  • Browser Automation (20)

  • Software Development (28)

  • Desktop Automation (17)

  • Social & Messaging (13)

  • Security & Reverse Engineering (21)

  • Design & Visualization (11)

  • Knowledge & Memory (27)

  • Agent Platforms (23)

  • Media & Creativity (15)

  • Finance & Trading (10)

  • Other MCP Servers (27)

• MCP Clients

  • CLI Tools (20)

  • Desktop & Mobile Clients (20)

  • IDE Extensions & Code Assistants (8)

  • Agent Orchestration Platforms (12)

  • Domain-Specific Integrations (7)

• MCP Frameworks and libraries

  • Python (45)

  • TypeScript (37)

  • Go (7)

  • C# (3)

  • Kotlin (3)

  • Java (6)

  • PHP (1)

  • Ruby (2)

  • Rust (2)

  • Swift (2)

• MCP Utilities & Tools

  • Testing & Debugging (6)

  • Gateways (13)

• MCP Resources & Educational Materials (20)

MCP Servers

Databases

• Canner/wren-engine (★360 Java) - Wren Engine is a semantic engine for Model Context Protocol (MCP) clients and AI agents that enables precise, context-aware access to enterprise business data with governance and interoperability.
• ClickHouse/mcp-clickhouse (★429 Python) - ClickHouse MCP Server is an MCP protocol implementation that enables secure, read-only SQL querying and database exploration for ClickHouse clusters, integrated with Claude Desktop and supporting local and cloud deployments.
• FreePeak/db-mcp-server (★227 Go) - FreePeak/db-mcp-server is a multi-database server implementing the Model Context Protocol (MCP) to enable AI assistants to access and manage multiple databases through a unified and structured interface.
• QuantGeekDev/mongo-mcp (★154 TypeScript) - mongo-mcp is a Model Context Protocol server that enables large language models to interact with MongoDB databases through natural language commands, supporting querying, schema inspection, and data management.
• XGenerationLab/xiyan_mcp_server (★173 Python) - XiYan MCP Server is an MCP server that enables natural language queries to databases by converting text inputs into SQL using state-of-the-art models like XiYan-SQL, supporting both remote and local deployment modes.
• alexander-zuev/supabase-mcp-server (★749 Python) - An open-source MCP server for Supabase enabling safe SQL query execution, schema management, and Supabase API integration via a chat interface.
• benborla/mcp-server-mysql (★582 TypeScript) - mcp-server-mysql is a Model Context Protocol server that provides secure, read-only access to MySQL databases, enabling large language models to inspect schemas and execute SQL queries efficiently.
• blurrah/mcp-graphql (★208 TypeScript) - mcp-graphql is an MCP server that enables large language models to dynamically interact with GraphQL APIs through schema introspection and query execution.
• bytebase/dbhub (★830 TypeScript) - DBHub is a universal database gateway implementing the Model Context Protocol (MCP) server interface, enabling MCP clients to connect to and explore multiple database systems including MySQL, PostgreSQL, Oracle, SQL Server, MariaDB, and SQLite.
• centralmind/gateway (★413 Go) - CentralMind Gateway is a universal MCP server that automatically generates secure, AI-optimized APIs for structured databases, enabling seamless integration with AI agents and LLMs via MCP and OpenAPI protocols.
• chatmcp/mcpso (★1770 TypeScript) - A directory platform for discovering and exploring Awesome MCP Servers, supporting the MCP ecosystem through server discovery and community engagement.
• chroma-core/chroma-mcp (★214 Python) - Chroma MCP Server is an implementation of the Model Context Protocol that provides advanced database capabilities for managing and retrieving contextual data collections in LLM applications using Chroma.
• cr7258/elasticsearch-mcp-server (★167 Python) - An MCP server implementation enabling interaction with Elasticsearch and OpenSearch clusters for document search, index analysis, and cluster management through natural language commands and APIs.
• crystaldba/postgres-mcp (★603 Python) - Postgres MCP Pro is an open-source Model Context Protocol server for PostgreSQL that provides advanced database health monitoring, index tuning, query plan analysis, and safe SQL execution to support AI agents and developers throughout the application lifecycle.
• danhilse/notion_mcp (★185 Python) - A simple MCP server integration that enables managing a personal Notion todo list through Claude with basic task management features.
• dbt-labs/dbt-mcp (★284 Python) - dbt-labs/dbt-mcp is an MCP server that enables standardized interaction with dbt, facilitating data model management and querying through the Model Context Protocol.
• designcomputer/mysql_mcp_server (★670 Python) - MySQL MCP Server is a Model Context Protocol implementation that enables secure and structured interaction between AI applications and MySQL databases through a controlled server interface.
• domdomegg/airtable-mcp-server (★190 TypeScript) - A Model Context Protocol server that enables AI systems to read, write, and manage Airtable databases by providing schema inspection and record manipulation capabilities.
• elastic/mcp-server-elasticsearch (★317 JavaScript) - Elasticsearch MCP Server is an experimental project that connects Elasticsearch data to MCP Clients, enabling natural language interaction with Elasticsearch indices and search capabilities through the Model Context Protocol.
• furey/mongodb-lens (★171 JavaScript) - MongoDB Lens is a full-featured local Model Context Protocol server that enables natural language interaction with MongoDB databases using large language models for querying, aggregation, optimization, and management.
• gannonh/firebase-mcp (★177 TypeScript) - Firebase MCP is an MCP server enabling AI assistants to interact with Firebase services like Firestore, Storage, and Authentication through the Model Context Protocol.
• genomoncology/biomcp (★164 Python) - BioMCP is an open-source toolkit implementing the Model Context Protocol to connect AI systems with authoritative biomedical data sources, enabling precise and in-depth answers about clinical trials, scientific literature, and genomic variants.
• googleapis/genai-toolbox (★1708 Go) - MCP Toolbox for Databases is an open-source MCP server that simplifies and secures generative AI tool development by providing efficient database access and management through a centralized control plane.
• julien040/anyquery (★1010 Go) - Anyquery is an extensible SQL query engine that enables querying diverse data sources and applications with SQL and connects to large language models using the Model Context Protocol (MCP).
• kiliczsh/mcp-mongo-server (★242 TypeScript) - MCP MongoDB Server is a Model Context Protocol server that enables large language models to interact with MongoDB databases by providing schema inspection and execution of MongoDB operations through a standardized interface.
• kruskal-labs/toolfront (★193 Python) - ToolFront is a project that enables AI agents to seamlessly connect with and learn from big data sources through the Model Context Protocol, enhancing AI's ability to query and understand large databases and APIs efficiently.
• makenotion/notion-mcp-server (★2437 TypeScript) - The Notion MCP Server is an official MCP server implementation that enables secure, programmatic interaction with Notion content through MCP commands, optimized for AI agents and supporting multiple deployment options.
• mindsdb/mindsdb (★33257 Python) - MindsDB is an AI-powered federated query engine and platform with an MCP server that enables querying and learning from large-scale, disparate data sources using natural language and SQL.
• mongodb-js/mongodb-mcp-server (★379 TypeScript) - mongodb-js/mongodb-mcp-server is a Model Context Protocol server enabling standardized interaction and management of MongoDB databases and MongoDB Atlas clusters through MCP tools.
• motherduckdb/mcp-server-motherduck (★233 Python) - MotherDuck's DuckDB MCP Server is an MCP server implementation that enables SQL analytics on DuckDB and MotherDuck databases, providing seamless data querying capabilities to AI Assistants and IDEs through the Model Context Protocol.
• neo4j-contrib/mcp-neo4j (★481 Python) - This project implements the Model Context Protocol (MCP) for Neo4j, enabling natural language interaction with Neo4j graph databases and cloud services through various MCP clients.
• neondatabase-labs/mcp-server-neon (★349 TypeScript) - Neon MCP Server is an open-source tool that enables natural language interaction with Neon Postgres databases via the Model Context Protocol, simplifying database management and migrations through conversational commands.
• qdrant/mcp-server-qdrant (★746 Python) - mcp-server-qdrant is an official Model Context Protocol server implementation for Qdrant that enables semantic memory management and integration with LLM applications through vector search.
• runekaagaard/mcp-alchemy (★257 Python) - MCP Alchemy is an MCP server that enables large language models like Claude Desktop to access, understand, and interact with various relational databases through SQL queries and schema exploration.
• suekou/mcp-notion-server (★769 TypeScript) - Notion MCP Server is an MCP server that enables large language models to efficiently interact with Notion workspaces by converting content to Markdown to optimize token usage.
• supabase-community/supabase-mcp (★1722 TypeScript) - Supabase MCP Server connects Supabase projects to AI assistants using the Model Context Protocol, enabling LLMs to manage and query Supabase resources.
• weaviate/mcp-server-weaviate (★134 Python) - Weaviate MCP Server integrates Model Context Protocol functionalities into the Weaviate vector search environment to enable context-aware data insertion and hybrid search capabilities.
• wenb1n-dev/mysql_mcp_server_pro (★207 Python) - mcp_mysql_server_pro is a MySQL Model Context Protocol server that supports CRUD operations, database anomaly analysis, permission control, and extensible custom tools, operating in multiple MCP transfer modes including SSE and STDIO.
• zilliztech/mcp-server-milvus (★155 Python) - MCP Server for Milvus is an implementation of the Model Context Protocol that enables LLM applications to seamlessly interact with the Milvus vector database for advanced search and data management capabilities.

Cloud & DevOps

• 1Panel-dev/mcp-1panel (★133 Go) - mcp-1panel is an MCP server implementation for 1Panel that enables clients to interact with and manage 1Panel services through the Model Context Protocol.
• Azure/azure-mcp (★890 PowerShell) - The Azure MCP Server is a Microsoft Azure project implementing the Model Context Protocol to enable AI agents to interact naturally and seamlessly with various Azure cloud services through natural language commands.
• DefangLabs/defang (★139 Go) - Defang is a platform with a CLI and MCP Server that enables developers to efficiently build, test, and deploy applications from Docker Compose to scalable cloud environments directly from terminals or IDEs.
• Flux159/mcp-server-kubernetes (★821 TypeScript) - MCP Server Kubernetes is an MCP server that connects to Kubernetes clusters to manage resources and execute Kubernetes commands programmatically or via chat interfaces.
• GoogleCloudPlatform/cloud-run-mcp (★242 JavaScript) - cloud-run-mcp is an MCP server that enables AI agents and applications to securely deploy and manage code on Google Cloud Run, supporting both local and remote deployment scenarios.
• QuantGeekDev/docker-mcp (★329 Python) - docker-mcp is a Model Context Protocol server that enables Docker container and Compose stack management through Claude AI, providing tools for container creation, deployment, log retrieval, and monitoring.
• RafalWilinski/aws-mcp (★278 TypeScript) - AWS MCP is an MCP server that enables AI assistants like Claude to interact with AWS environments using natural language for querying and managing resources.
• StacklokLabs/toolhive (★235 Go) - ToolHive is a lightweight CLI utility that simplifies and secures the deployment and management of Model Context Protocol (MCP) servers using containerization and enterprise-grade authorization controls.
• Tiberriver256/mcp-server-azure-devops (★273 TypeScript) - An MCP server implementation for Azure DevOps that enables AI assistants to interact with Azure DevOps APIs through a standardized protocol, supporting secure authentication and a variety of DevOps operations.
• YanxingLiu/dify-mcp-server (★246 Python) - dify-mcp-server is an MCP server implementation that enables the invocation of dify workflows through MCP tools, facilitating integration and automation within MCP-compatible clients.
• akuity/argocd-mcp (★165 TypeScript) - argocd-mcp is an MCP server implementation for Argo CD that enables AI assistants to manage Kubernetes applications through natural language interaction and integrates with various MCP clients.
• alexei-led/aws-mcp-server (★141 Python) - AWS MCP Server is a lightweight service that enables AI assistants to securely execute AWS CLI commands through the Model Context Protocol, enhancing cloud infrastructure management.
• alexei-led/k8s-mcp-server (★151 Python) - K8s MCP Server is a Docker-based implementation of Anthropic's Model Context Protocol that enables AI assistants like Claude to securely execute Kubernetes CLI commands for AI-driven cluster management and troubleshooting.
• alexei-led/spotinfo (★131 Go) - Spotinfo is a CLI tool and MCP server for exploring AWS EC2 Spot Instances, providing real-time placement scores, pricing, and interruption data with advanced filtering and AI assistant integration.
• anaisbetts/mcp-installer (★1266 JavaScript) - mcp-installer is an MCP server that automates the installation of other MCP servers via natural language commands to Claude, supporting packages from npm and PyPi.
• apache/apisix (★15313 Lua) - Apache APISIX is a high-performance cloud-native API Gateway and AI Gateway that supports Model Context Protocol (MCP) integration through its mcp-bridge plugin, offering dynamic traffic management, security, and observability features.
• awslabs/mcp (★4369 Python) - AWS MCP Servers is a suite of specialized Model Context Protocol servers that integrate AWS best practices and resources into AI-powered development workflows to enhance cloud-native development and infrastructure management.
• beclab/Olares (★2104 Shell) - Olares is an open-source personal cloud operating system that enables users to run local AI models and applications with personalized, context-aware AI interactions using a Model Context Protocol-like mechanism, providing a private and secure AI home server environment.
• ckreiling/mcp-server-docker (★517 Python) - An MCP server that enables natural language management of Docker containers, allowing users to compose, debug, and manage containers and volumes through AI-driven conversational interactions.
• cloudflare/mcp-server-cloudflare (★2648 TypeScript) - Cloudflare MCP Server is a suite of MCP servers that enable large language model clients to interact with and manage Cloudflare's cloud services through natural language commands, facilitating automation and insights across various domains.
• grafana/mcp-grafana (★1082 Go) - mcp-grafana is an MCP server that provides comprehensive programmatic access to Grafana's dashboards, datasources, alerts, incidents, and on-call management features through MCP clients.
• hashicorp/terraform-mcp-server (★680 Go) - Terraform MCP Server is an MCP server that integrates with Terraform Registry APIs to automate and enhance Infrastructure as Code development workflows.
• leonardsellem/n8n-mcp-server (★686 TypeScript) - n8n MCP Server is an MCP server that enables AI assistants to manage and execute n8n workflows through natural language commands and API integration.
• manusa/kubernetes-mcp-server (★356 Go) - kubernetes-mcp-server is a native Model Context Protocol server implementation that enables flexible and powerful management of Kubernetes and OpenShift clusters without external dependencies.
• merill/lokka (★140 JavaScript) - Lokka is an MCP server that enables AI-driven natural language querying and management of Microsoft 365 and Azure tenants via Microsoft Graph and Azure Resource Management APIs.
• metorial/mcp-containers (★1905 TypeScript) - MCP Containers offers containerized versions of hundreds of MCP servers, enabling easy, secure, and up-to-date deployment of Model Context Protocol servers for AI integration and experimentation.
• mikegc-aws/Lambda-MCP-Server (★192 Python) - Lambda MCP Server is a serverless MCP tool server implementation on AWS Lambda with streaming HTTP, session management, and integration with Amazon Bedrock and Nova Pro for intelligent agents.
• modelcontextprotocol/registry (★1834 Go) - MCP Registry is a community-driven centralized service offering a RESTful API for discovering, managing, and publishing Model Context Protocol (MCP) servers with MongoDB and Docker support.
• nwiizo/tfmcp (★315 Rust) - tfmcp is a CLI tool implementing the Model Context Protocol to enable AI assistants to efficiently manage and operate Terraform environments with advanced security and automation features.
• pab1it0/prometheus-mcp-server (★142 Python) - Prometheus MCP Server is an MCP server that enables AI assistants to query and analyze Prometheus metrics through standardized MCP interfaces with support for authentication and Docker deployment.
• ravitemer/mcp-hub (★182 JavaScript) - MCP Hub is a centralized management server that coordinates multiple MCP servers, providing dynamic server management, real-time monitoring, and unified API access according to the MCP 2025-03-26 specification.
• rohitg00/awesome-devops-mcp-servers (★569 ) - A curated list of Model Context Protocol (MCP) servers focused on DevOps tools and capabilities, enabling AI-driven management of cloud infrastructure, container orchestration, and cloud services.
• rohitg00/kubectl-mcp-server (★650 Python) - kubectl-mcp-server is an MCP server for Kubernetes that enables AI assistants to manage Kubernetes clusters through natural language commands, providing comprehensive cluster operations, monitoring, security, and diagnostics.
• stacklok/toolhive (★701 Go) - ToolHive is a CLI utility that simplifies and secures the deployment and management of Model Context Protocol (MCP) servers using containerization and standardized packaging.
• strowk/mcp-k8s-go (★313 Go) - mcp-k8s-go is a Golang-based MCP server that connects to Kubernetes clusters, enabling users to manage and query Kubernetes resources through the Model Context Protocol interface.

Browser Automation

• AgentDeskAI/browser-tools-mcp (★5581 JavaScript) - BrowserTools MCP is a powerful browser monitoring and interaction tool that leverages the Model Context Protocol to enable AI-powered applications to capture and analyze browser data directly within MCP-compatible IDEs.
• Automata-Labs-team/MCP-Server-Playwright (★218 JavaScript) - MCP Server Playwright is an MCP server that enables large language models to perform comprehensive browser automation tasks such as navigation, interaction, screenshot capture, and JavaScript execution using Playwright in a real browser environment.
• BrowserMCP/mcp (★2826 TypeScript) - Browser MCP is an MCP server and Chrome extension that enables AI applications to automate and control your browser locally using your existing browser profile for privacy, speed, and stealth.
• OTA-Tech-AI/web-agent-protocol (★471 Python) - Web Agent Protocol (WAP) is a standardized framework that records and replays user interactions in browsers with support for Model Context Protocol (MCP), enabling efficient automation and reuse of browser actions.
• Operative-Sh/web-eval-agent (★1080 Python) - Operative-Sh/web-eval-agent is an MCP server that autonomously evaluates and debugs web applications by navigating, capturing network traffic, and collecting console errors to verify code functionality end-to-end.
• Skyvern-AI/skyvern (★13749 Python) - Skyvern automates browser-based workflows using large language models and computer vision, providing a robust and scalable web automation solution that integrates with the Model Context Protocol (MCP).
• aaronjmars/opendia (★234 JavaScript) - OpenDia is a privacy-first browser automation tool that connects AI models to Chromium-based browsers using the Model Context Protocol, enabling seamless AI-driven interactions and automation without switching browsers.
• apify/actors-mcp-server (★245 TypeScript) - Apify MCP Server is an MCP protocol server implementation that enables AI assistants to interact with Apify Actors for data extraction, web scraping, and automation tasks through a standardized protocol.
• apify/mcp-server-rag-web-browser (★157 JavaScript) - An MCP server implementation enabling AI agents to perform efficient web searches and content extraction via the RAG Web Browser Actor using the Model Context Protocol.
• brightdata/brightdata-mcp (★819 JavaScript) - Bright Data MCP is a Model Context Protocol server that enables AI agents and applications to access and extract real-time web data seamlessly, enhancing their capabilities with live information.
• browser-use/vibetest-use (★445 Python) - Vibetest MCP is an automated QA testing tool using Browser-Use agents within the MCP framework to detect UI bugs, broken links, and accessibility issues on vibe-coded websites.
• browserbase/mcp-server-browserbase (★2116 TypeScript) - Browserbase MCP Server enables LLMs to control and interact with web browsers using the Model Context Protocol, providing cloud browser automation and advanced web interaction capabilities.
• co-browser/browser-use-mcp-server (★605 Python) - browser-use-mcp-server is an MCP server that enables AI agents to control web browsers using browser automation with support for multiple transport protocols and real-time VNC streaming.
• executeautomation/mcp-playwright (★4155 TypeScript) - executeautomation/mcp-playwright is a Model Context Protocol server that enables AI-driven browser automation and web interactions using Playwright.
• hyperbrowserai/mcp (★383 TypeScript) - Hyperbrowser MCP Server is an implementation of the Model Context Protocol providing AI-powered tools for web scraping, data extraction, and browser automation using various browser agents.
• jae-jae/fetcher-mcp (★750 TypeScript) - Fetcher MCP is an MCP server that uses Playwright to fetch and intelligently extract web page content, supporting JavaScript execution, parallel processing, and flexible output formats.
• jae-jae/g-search-mcp (★166 TypeScript) - g-search-mcp is a powerful MCP server enabling parallel Google searches with multiple keywords, featuring CAPTCHA handling, user behavior simulation, and configurable parameters for efficient automated search tasks.
• mendableai/firecrawl-mcp-server (★3683 JavaScript) - Firecrawl MCP Server is an MCP server implementation that integrates web scraping capabilities with LLM clients like Cursor and Claude to enable advanced content extraction and research.
• microsoft/playwright-mcp (★13903 TypeScript) - Playwright MCP is an MCP server that enables LLMs to automate and interact with web browsers using structured accessibility snapshots for efficient and deterministic browser automation.
• mzxrai/mcp-webresearch (★264 JavaScript) - MCP Web Research Server is an MCP server that integrates real-time web research capabilities into Claude, enabling interactive and sourced information retrieval from the internet.

Software Development

• Coding-Solo/godot-mcp (★575 JavaScript) - Godot MCP is an MCP server that enables AI assistants to interact with the Godot game engine by launching editors, running projects, capturing debug output, and managing scenes through a standardized interface.
• JetBrains/mcp-jetbrains (★819 JavaScript) - JetBrains MCP Proxy Server is an MCP server that enables communication and integration between JetBrains IDEs and external clients, enhancing interoperability and AI-assisted development workflows.
• RaiAnsar/claude_code-gemini-mcp (★190 Python) - This project implements an MCP server that integrates Claude Code with Google's Gemini AI, enabling AI collaboration for questions, code reviews, and brainstorming within the Claude Code environment.
• SDGLBL/mcp-claude-code (★206 Python) - MCP Claude Code is an MCP server implementation that enables Claude to perform secure and multi-agent supported code analysis, modification, and project file management using the Model Context Protocol.
• admica/FileScopeMCP (★180 TypeScript) - FileScopeMCP is a TypeScript-based MCP server that analyzes codebases to rank file importance, track dependencies, and generate visualizations, enhancing AI-assisted code understanding.
• apollographql/apollo-mcp-server (★148 Rust) - Apollo MCP Server exposes GraphQL operations as Model Context Protocol (MCP) tools, enabling integration of GraphQL within the MCP ecosystem.
• biegehydra/BifrostMCP (★136 TypeScript) - BifrostMCP is a VSCode extension that provides an MCP server exposing VSCode's language features to AI assistants for advanced code navigation, analysis, and manipulation.
• bigcodegen/mcp-neovim-server (★177 TypeScript) - mcp-neovim-server is a proof of concept MCP server that integrates Neovim with AI clients like Claude Desktop to enable AI-assisted text editing using the Model Context Protocol.
• cameroncooke/XcodeBuildMCP (★1895 TypeScript) - XcodeBuildMCP is an MCP server that provides Xcode-related tools enabling AI agents to autonomously manage, build, and interact with Xcode projects and iOS simulators for automated development workflows.
• comet-ml/opik (★10672 Python) - Opik is an open-source platform for debugging, evaluating, and monitoring large language model applications with comprehensive tracing, automated evaluations, and production-ready dashboards.
• context-hub/generator (★143 PHP) - CTX is a tool that generates structured context documentation from various sources and serves it via an MCP server to enable AI models like Claude to access and understand codebases efficiently.
• e2b-dev/mcp-server (★281 JavaScript) - The e2b-dev/mcp-server project is an MCP server that enables Claude Desktop to run code via the E2B Sandbox, supporting JavaScript and Python editions for enhanced code interpreting capabilities.
• ee0pdt/Godot-MCP (★237 GDScript) - Godot MCP is a plugin that integrates the Godot game engine with AI assistants using the Model Context Protocol, enabling natural language interaction for game development tasks such as scripting, scene editing, and project management.
• github/github-mcp-server (★16815 Go) - GitHub MCP Server is an official Model Context Protocol server that integrates with GitHub APIs to enable advanced automation and AI-powered interactions with GitHub repositories and workflows.
• idosal/git-mcp (★3296 TypeScript) - GitMCP is an open-source remote Model Context Protocol server that transforms GitHub projects into AI-accessible documentation hubs to eliminate code hallucinations and provide accurate, up-to-date code information.
• isaacphi/mcp-language-server (★621 Go) - The mcp-language-server is an MCP server that exposes language servers to MCP clients, enabling advanced semantic code navigation and interaction for large language models and other MCP-enabled tools.
• jamubc/gemini-mcp-tool (★161 JavaScript) - gemini-mcp-tool is an MCP server that enables AI assistants to leverage Google Gemini CLI's large token window for advanced large file and codebase analysis within AI environments like Claude Code.
• janwilmake/openapi-mcp-server (★710 JavaScript) - OpenAPI MCP Server is an MCP server that enables AI models to explore and understand OpenAPI specifications using simple language for easier API integration and usage.
• jasonjmcghee/claude-debugs-for-you (★374 TypeScript) - Claude Debugs For You is a VS Code extension and MCP server that enables large language models like Claude to interactively debug code in any language using breakpoints and expression evaluation.
• jerhadf/linear-mcp-server (★309 JavaScript) - The Linear MCP Server is an MCP server that integrates Linear's project management system with the Model Context Protocol, enabling LLMs to interact with Linear issues through tools for creating, updating, searching, and commenting on issues.
• juehang/vscode-mcp-server (★139 TypeScript) - A Visual Studio Code extension implementing a Model Context Protocol server that exposes VS Code editing and filesystem features to AI models and MCP clients for enhanced AI-assisted coding workflows.
• oraios/serena (★3414 Python) - Serena is a free and open-source coding agent toolkit that uses the Model Context Protocol to enable LLMs to autonomously perform semantic code retrieval and editing with IDE-like precision on complex codebases.
• r-huijts/xcode-mcp-server (★276 TypeScript) - Xcode MCP Server is an MCP server implementation that enables AI assistants to interact with Xcode projects, manage iOS simulators, and perform various Xcode-related tasks through the Model Context Protocol.
• rusiaaman/wcgw (★532 Python) - wcgw is an MCP server that integrates shell and coding tools to enable AI-assisted coding, building, and running tasks on local machines through the Claude desktop app and other MCP clients.
• snagasuri/deebo-prototype (★615 JavaScript) - Deebo is an autonomous debugging agent MCP server that accelerates AI coding agents' debugging process by launching automated investigations and providing multi-threaded debugging support.
• sooperset/mcp-atlassian (★2281 Python) - MCP Atlassian is an MCP server enabling AI-powered automation and interaction with Atlassian tools like Confluence and Jira across Cloud and Server deployments.
• steipete/claude-code-mcp (★446 JavaScript) - Claude Code MCP Server is an MCP server that integrates Claude Code as a one-shot tool with automatic permissions bypass, enhancing AI agents' coding and file operation capabilities within the MCP ecosystem.
• upstash/context7 (★17516 JavaScript) - Context7 MCP Server is an MCP server that delivers up-to-date, version-specific code documentation and examples to enhance LLMs and AI code editors, ensuring accurate and current code generation.

Desktop Automation

• BandarLabs/coderunner (★150 Python) - CodeRunner is an MCP server that securely executes AI-generated code locally on macOS using Apple's container technology, enabling private and efficient processing of local files with remote LLMs.
• CursorTouch/Windows-MCP (★136 Python) - Windows-MCP is a lightweight, open-source MCP server that enables seamless integration and automation between AI agents using LLMs and the Windows operating system, supporting a wide range of UI interactions and system controls.
• InditexTech/mcp-server-simulator-ios-idb (★199 TypeScript) - An MCP server that enables Large Language Models to control iOS simulators through natural language commands for comprehensive simulator and app management, UI interaction, and debugging.
• Omar-V2/mcp-ical (★141 Python) - mcp-ical is an MCP server that enables natural language interaction with macOS Calendar for creating, managing, and querying events through conversational commands.
• ashwwwin/automation-mcp (★243 TypeScript) - Automation MCP is a Model Context Protocol server that enables AI models to perform comprehensive desktop automation on macOS, including mouse, keyboard, screen, and window management.
• baryhuang/mcp-remote-macos-use (★211 Python) - An open-source MCP server enabling autonomous AI agents to fully control remote macOS systems through Claude Desktop without extra API keys or software installations.
• bytedance/UI-TARS-desktop (★14952 TypeScript) - UI-TARS Desktop is a cross-platform GUI Agent application that uses a vision-language model to enable natural language control of computers with precise visual recognition and real-time feedback, integrating Model Context Protocol tools for advanced multimodal AI-driven automation.
• claude-did-this/MCPControl (★154 TypeScript) - MCPControl is a Windows server implementing the Model Context Protocol to enable AI-driven programmatic control of mouse, keyboard, windows, screen capture, and clipboard operations for automation and experimentation.
• dvcrn/mcp-server-siri-shortcuts (★144 TypeScript) - An MCP server that enables large language models to list, open, and run Siri Shortcuts on macOS through the Model Context Protocol.
• ferrislucas/iterm-mcp (★379 TypeScript) - iterm-mcp is a Model Context Protocol server that enables AI models to interact with and control an iTerm terminal session for enhanced REPL and CLI assistance.
• joshrutkowski/applescript-mcp (★235 TypeScript) - applescript-mcp is a Model Context Protocol server that enables AI applications to interact with macOS through AppleScript, providing extensive control over system functions, files, notifications, and more.
• joshuayoes/ios-simulator-mcp (★583 JavaScript) - ios-simulator-mcp is an MCP server enabling AI-driven interaction, control, and inspection of iOS simulators for automated UI testing and quality assurance.
• mamertofabian/mcp-everything-search (★207 Python) - mcp-everything-search is a cross-platform MCP server that provides fast and versatile file searching capabilities by integrating platform-specific search tools like Everything SDK, mdfind, and locate into the MCP ecosystem.
• peakmojo/applescript-mcp (★298 Python) - An MCP server that executes AppleScript to provide full control and automation of Mac applications and system features through simple and minimal setup.
• recursechat/mcp-server-apple-shortcuts (★197 JavaScript) - An MCP server that enables AI assistants like Claude to safely control and automate Apple Shortcuts on macOS.
• steipete/Peekaboo (★261 TypeScript) - Peekaboo is a macOS-only MCP server and CLI tool that enables AI agents to capture and analyze screenshots with AI vision models for visual question answering and automation.
• wonderwhy-er/DesktopCommanderMCP (★3760 TypeScript) - Desktop Commander MCP is an MCP server for Claude that integrates AI with terminal control, file system search, and file editing capabilities, enabling advanced desktop automation and development workflows.

Social & Messaging

• BurtTheCoder/mcp-maigret (★140 JavaScript) - mcp-maigret is an MCP server integrating the Maigret OSINT tool to perform username searches and URL analyses across social networks, providing multi-format reports and seamless integration with MCP-compatible applications like Claude Desktop.
• EnesCinr/twitter-mcp (★236 TypeScript) - twitter-mcp is an MCP server that enables clients to post and search tweets on Twitter through the Model Context Protocol.
• GongRzhe/Gmail-MCP-Server (★476 JavaScript) - Gmail AutoAuth MCP Server is an MCP server that enables AI assistants to manage Gmail through natural language commands with full Gmail API integration and OAuth2 authentication support.
• InditexTech/mcp-teams-server (★267 Python) - MCP Teams Server is an MCP protocol server implementation enabling Microsoft Teams integration with capabilities to read, create, reply to messages, and mention members within Teams channels.
• abhiz123/todoist-mcp-server (★275 JavaScript) - Todoist MCP Server is an MCP server implementation that integrates Claude AI with Todoist, enabling natural language task management including creating, updating, completing, and deleting tasks.
• adhikasp/mcp-linkedin (★137 Python) - mcp-linkedin is an MCP server that enables automated interaction with LinkedIn's Feeds and Job API for data retrieval and analysis within the MCP ecosystem.
• adhikasp/mcp-twikit (★181 Python) - mcp-twikit is an MCP server that enables Twitter interaction, including tweet search, timeline retrieval, and sentiment analysis, through the Model Context Protocol framework.
• chatmcp/mcp-server-chatsum (★999 TypeScript) - mcp-server-chatsum is an MCP server that enables querying and summarizing chat messages to facilitate efficient chat data management and review.
• chigwell/telegram-mcp (★218 Python) - Telegram MCP Server is a full-featured integration that enables programmatic interaction with Telegram accounts through the Model Context Protocol, providing extensive tools for messaging, chat and group management, contact handling, and more.
• korotovsky/slack-mcp-server (★207 Go) - A feature-rich Model Context Protocol (MCP) server for Slack Workspaces supporting stealth and OAuth modes, multiple transports, proxy settings, and comprehensive Slack message and channel interactions without requiring workspace permissions or bot approvals.
• lharries/whatsapp-mcp (★4305 Go) - WhatsApp MCP Server is an MCP server that enables AI-driven interaction with personal WhatsApp messages and media through integration with LLMs like Claude, using a Go bridge and Python MCP server architecture.
• line/line-bot-mcp-server (★421 JavaScript) - An MCP server implementation that integrates the LINE Messaging API to connect AI Agents with LINE Official Accounts for automated and customizable messaging.
• pipeboard-co/meta-ads-mcp (★144 Python) - Meta Ads MCP is an MCP server that enables AI models to access, analyze, and manage advertising campaigns on Meta platforms like Facebook and Instagram through a standardized interface.

Security & Reverse Engineering

• 0xKoda/WireMCP (★159 JavaScript) - WireMCP is an MCP server that empowers Large Language Models with real-time network traffic analysis using Wireshark's tshark tool to provide structured context for threat detection, diagnostics, and anomaly identification.
• Automata-Labs-team/code-sandbox-mcp (★226 Go) - code-sandbox-mcp is an MCP server providing a secure, isolated Docker-based sandbox environment for safe code execution within AI applications.
• BlackSnufkin/LitterBox (★965 YARA) - LitterBox is a secure sandbox environment integrating with LLM agents via MCP to provide advanced malware analysis and testing capabilities for red and blue teams before deployment.
• LaurieWired/GhidraMCP (★5306 Java) - GhidraMCP is an MCP server that integrates Ghidra's reverse engineering capabilities with MCP clients, enabling automated binary analysis and decompilation through large language models.
• MorDavid/BloodHound-MCP-AI (★235 Python) - BloodHound-MCP-AI integrates BloodHound with AI through the Model Context Protocol, enabling natural language analysis of Active Directory attack paths for enhanced security assessment.
• PortSwigger/mcp-server (★196 Kotlin) - PortSwigger/mcp-server is a Burp Suite extension implementing a Model Context Protocol server to integrate Burp with AI clients for advanced AI-driven security testing and automation workflows.
• SimonB97/win-cli-mcp-server (★217 JavaScript) - A secure and configurable Model Context Protocol server for Windows enabling multi-shell command-line interactions and remote SSH management with extensive security controls.
• ant4g0nist/lisa.py (★729 Python) - LLDB MCP Integration enables AI assistants like Claude to interact with LLDB debugging sessions through the Model-Context Protocol, facilitating natural language debugging commands and automation.
• cyproxio/mcp-for-security (★275 TypeScript) - MCP for Security is a collection of Model Context Protocol servers that integrate popular security and penetration testing tools into AI workflows through a standardized interface.
• fiddlecube/compliant-llm (★142 Python) - Compliant LLM is a comprehensive toolkit for building secure and compliant AI agents and MCP servers, supporting multiple LLM providers and ensuring adherence to major compliance frameworks like NIST, ISO, HIPAA, and GDPR.
• g0t4/mcp-server-commands (★168 TypeScript) - mcp-server-commands is an MCP server that enables large language models to securely execute shell commands and interact with the system environment.
• invariantlabs-ai/mcp-scan (★859 Python) - MCP-Scan is a security tool that statically and dynamically scans and monitors Model Context Protocol (MCP) connections to detect and prevent vulnerabilities such as prompt injections, tool poisoning, and cross-origin escalations.
• mariocandela/beelzebub (★1203 Go) - Beelzebub is a secure low-code honeypot framework leveraging large language models and the Model Context Protocol (MCP) to detect and analyze cyber attacks, including prompt injection attempts against LLM agents.
• mrexodia/ida-pro-mcp (★2525 Python) - ida-pro-mcp is an MCP server for IDA Pro that enables advanced reverse engineering capabilities through MCP-based interactions and automation.
• safedep/vet (★522 Go) - safedep/vet is an enterprise-grade open source software supply chain security tool offering next-generation software composition analysis, real-time malicious package detection, policy as code, and multi-ecosystem support, with integration into CI/CD workflows and MCP server capabilities.
• semgrep/mcp (★211 Python) - semgrep/mcp is an MCP server that integrates Semgrep's static code analysis to scan code for security vulnerabilities within MCP-compatible tools and IDEs.
• splx-ai/agentic-radar (★616 Python) - Agentic Radar is a security scanner tool that analyzes, visualizes, and assesses vulnerabilities in large language model agentic workflows, including MCP server detection and mapping to known security frameworks.
• svnscha/mcp-windbg (★668 Python) - mcp-windbg is a Model Context Protocol server that enables AI models to analyze Windows crash dumps using WinDBG through natural language interaction and command execution.
• tuananh/hyper-mcp (★692 Rust) - hyper-mcp is a fast, secure Model Context Protocol server that extends AI capabilities through WebAssembly plugins, supporting diverse deployment environments and strong security features.
• zinja-coder/apktool-mcp-server (★144 Python) - apktool-mcp-server is an MCP server integrating Apk Tool with Model Context Protocol to provide live, AI-assisted Android APK reverse engineering and vulnerability analysis using LLMs like Claude.
• zinja-coder/jadx-ai-mcp (★353 Java) - JADX-AI-MCP is a JADX plugin integrating Model Context Protocol to enable AI-powered live reverse engineering, vulnerability detection, and code analysis of Android APKs using large language models like Claude.

Design & Visualization

• GLips/Figma-Context-MCP (★8814 TypeScript) - GLips/Figma-Context-MCP is an MCP server that provides Figma layout and design information to AI coding agents like Cursor, enabling accurate one-shot design implementation in code.
• GongRzhe/Office-PowerPoint-MCP-Server (★551 Python) - Office-PowerPoint-MCP-Server is a comprehensive MCP server enabling programmatic creation and manipulation of PowerPoint presentations using the MCP protocol and python-pptx, featuring 32 tools across 11 modules for professional presentation automation.
• VedantRGosavi/UE5-MCP (★282 ) - UE5-MCP is a Model Control Protocol implementation that integrates AI-driven automation into Blender and Unreal Engine 5 workflows to enhance game level creation, asset management, and gameplay programming.
• YuChenSSR/mindmap-mcp-server (★139 Python) - Mindmap MCP Server is an MCP server that converts Markdown content into interactive mindmaps with multiple output formats and integration support for MCP-compatible clients.
• ahujasid/blender-mcp (★12190 Python) - BlenderMCP integrates Blender with Claude AI using the Model Context Protocol to enable AI-driven 3D modeling, scene creation, and manipulation through two-way communication and command execution.
• antvis/mcp-server-chart (★1712 JavaScript) - mcp-server-chart is a TypeScript-based Model Context Protocol server by AntV that generates over 25 types of visual charts using the AntV library and returns image URLs for each chart.
• mapbox/mcp-server (★210 TypeScript) - Mapbox MCP Server is a Node.js implementation of the Model Context Protocol that provides AI applications with comprehensive geospatial intelligence and location-based services through Mapbox APIs.
• markmap/markmap (★11400 TypeScript) - Markmap is a tool that visualizes Markdown content as interactive mindmaps and includes an MCP Server for enhanced interoperability within the Model Context Protocol ecosystem.
• neka-nat/freecad-mcp (★191 Python) - FreeCAD MCP is an MCP server that enables automated and scripted control of FreeCAD through Claude Desktop for enhanced CAD modeling workflows.
• revit-mcp/revit-mcp (★177 TypeScript) - revit-mcp is an AI-powered MCP server that enables AI clients to interact with Autodesk Revit for creating, modifying, and managing building elements through the Model Context Protocol.
• sonnylazuardi/cursor-talk-to-figma-mcp (★4626 JavaScript) - Cursor Talk to Figma MCP integrates Cursor AI with Figma using the Model Context Protocol to enable programmatic reading and modification of Figma designs for enhanced design automation.

Knowledge & Memory

• 54yyyu/zotero-mcp (★160 Python) - Zotero MCP connects your Zotero research library with AI assistants like Claude via the Model Context Protocol, enabling advanced search, summaries, citation analysis, and PDF annotation extraction for enhanced research workflows.
• CheMiguel23/MemoryMesh (★269 TypeScript) - MemoryMesh is a knowledge graph server using the Model Context Protocol to provide structured memory persistence for AI models, especially suited for text-based RPGs and interactive storytelling.
• GreatScottyMac/context-portal (★422 Python) - Context Portal MCP (ConPort) is a database-backed MCP server that builds a structured project-specific knowledge graph to enable AI assistants to provide context-aware, accurate responses through Retrieval Augmented Generation in development environments.
• MarkusPfundstein/mcp-obsidian (★1335 Python) - MCP server enabling interaction with Obsidian via the Obsidian Local REST API community plugin, providing tools for file management, content retrieval, search, and content modification within Obsidian vaults.
• MicrosoftDocs/mcp (★602 ) - The Microsoft Learn Docs MCP Server is a cloud-hosted service implementing the Model Context Protocol to provide AI assistants with real-time access to official Microsoft documentation through semantic search and standardized endpoints.
• Olow304/memvid (★8126 Python) - Memvid is a video-based AI memory library that stores millions of text chunks in MP4 files with ultra-fast semantic search, eliminating the need for traditional databases and enabling portable, efficient AI memory management.
• RafalWilinski/mcp-apple-notes (★229 TypeScript) - MCP Apple Notes is an MCP server that enables semantic search and retrieval augmented generation over Apple Notes, allowing AI assistants like Claude to access and reference personal notes during conversations.
• StevenStavrakis/obsidian-mcp (★438 TypeScript) - obsidian-mcp is an MCP server that enables AI assistants to interact with Obsidian vaults, providing tools for managing notes and tags through reading, creating, editing, and organizing content.
• assafelovic/gptr-mcp (★205 Python) - GPT Researcher MCP Server is an MCP protocol-based server that enables LLM applications to perform deep, validated, and comprehensive web research, enhancing information quality and reasoning capabilities.
• basicmachines-co/basic-memory (★1037 Python) - Basic Memory is a knowledge management system that uses the Model Context Protocol to enable AI assistants to read and write structured knowledge stored locally in Markdown files, creating a persistent semantic graph for ongoing conversations and knowledge building.
• blazickjp/arxiv-mcp-server (★1354 Python) - ArXiv MCP Server is an MCP server that enables AI assistants to search, access, and analyze arXiv academic papers through a programmatic interface.
• casibase/casibase (★3796 Go) - Casibase is an open-source enterprise AI knowledge base platform supporting the Model Context Protocol and multiple AI models with features like admin UI, user management, and Single Sign-On.
• cyanheads/atlas-mcp-server (★231 TypeScript) - ATLAS MCP Server is a Neo4j-based Model Context Protocol server designed to manage projects, tasks, and knowledge in LLM agent workflows using a three-tier architecture.
• devflowinc/trieve (★2337 Rust) - Trieve is an all-in-one infrastructure platform offering advanced search, recommendations, retrieval-augmented generation, and analytics via API with strong support for Model Context Protocol (MCP) integration.
• dmayboroda/minima (★750 Python) - Minima is an open-source on-premises RAG system that enables secure, private querying of local documents through conversational AI with integration support for ChatGPT and the Model Context Protocol (MCP).
• doobidoo/mcp-memory-service (★432 Python) - MCP Memory Service is an MCP server that provides semantic memory and persistent storage for Claude Desktop, enabling long-term context-aware interactions through advanced semantic search and memory management.
• ggozad/haiku.rag (★250 Python) - Haiku SQLite RAG is a self-contained Retrieval-Augmented Generation library using SQLite that supports hybrid semantic and full-text search, multiple embedding and QA providers, and integrates with AI assistants via an MCP server.
• graphlit/graphlit-mcp-server (★324 TypeScript) - The graphlit-mcp-server is an MCP Server for the Graphlit Platform that centralizes diverse data sources into a searchable, RAG-ready knowledge base for MCP clients, supporting extensive data ingestion, retrieval, and integration capabilities.
• hannesrudolph/mcp-ragdocs (★203 TypeScript) - An MCP server implementation that enhances AI assistants by enabling semantic search and retrieval of documentation to augment responses with relevant context.
• mem0ai/mem0-mcp (★374 Python) - mem0-mcp is an MCP server integrated with mem0 that manages coding preferences by providing tools to store, retrieve, and semantically search coding patterns and solutions through an SSE endpoint accessible by clients like Cursor.
• reading-plus-ai/mcp-server-deep-research (★133 Python) - MCP Server for Deep Research is an MCP-based tool that transforms research questions into comprehensive, well-cited reports through a structured workflow involving question elaboration, subquestion generation, web search, content analysis, and report generation.
• scorzeth/anki-mcp-server (★140 JavaScript) - An MCP server implementation that connects to the Anki desktop app, enabling programmatic card review and creation through the Model Context Protocol.
• shaneholloman/mcp-knowledge-graph (★452 JavaScript) - mcp-knowledge-graph is an MCP server that provides persistent memory for AI models through a local knowledge graph, enabling user information retention across interactions and compatibility with any MCP-supporting AI platform.
• snexus/llm-search (★609 Jupyter Notebook) - snexus/llm-search is an advanced Retrieval-Augmented Generation system that enables efficient querying and interaction with local document collections using customizable Large Language Models and supports integration via an MCP server.
• spences10/mcp-sequentialthinking-tools (★225 TypeScript) - An MCP server that enhances problem-solving by guiding sequential thinking and providing confidence-scored recommendations for MCP tool usage at each step.
• supermemoryai/supermemory-mcp (★1099 TypeScript) - Supermemory MCP is a universal memory system that enables seamless access to personal memories across all large language models without requiring logins or paywalls.
• topoteretes/cognee (★6040 Jupyter Notebook) - Cognee is an open-source project that provides scalable and modular memory capabilities for AI agents using ECL pipelines, enabling efficient management and retrieval of past interactions and diverse data types.

Agent Platforms

• 53AI/53AIHub (★539 JavaScript) - 53AI Hub is an open-source AI portal that enables rapid building, deployment, and management of AI agents, prompts, and tools with seamless integration to multiple development and cloud platforms, supporting both cloud and local environments.
• ArcadeAI/arcade-ai (★506 Python) - Arcade AI Platform is a modular developer platform for building, deploying, and managing AI agent tools, featuring serving infrastructure for Model Context Protocol (MCP) servers.
• EvolutionAPI/evo-ai (★399 TypeScript) - Evo AI is an open-source platform for creating, managing, and integrating diverse AI agents with support for Model Context Protocol and Google's Agent 2 Agent interoperability protocol.
• FradSer/mcp-server-mas-sequential-thinking (★204 Python) - An advanced Multi-Agent System for sequential thinking implemented with the Agno framework and served via MCP, enabling coordinated specialized agents to collaboratively analyze and synthesize complex thoughts for deeper problem-solving.
• GaiaNet-AI/gaianet-node (★4972 Shell) - GaiaNet Node is a decentralized AI agent platform that enables users to install, configure, and run their own AI nodes using open-source models and vector databases in a distributed network.
• Klavis-AI/klavis (★2856 TypeScript) - Klavis AI is an open-source platform offering production-ready Model Context Protocol (MCP) servers and clients for seamless integration and scaling of AI applications across multiple platforms with built-in authentication and extensive tool support.
• Mintplex-Labs/anything-llm (★46036 JavaScript) - AnythingLLM is an all-in-one AI application with full MCP compatibility that enables intelligent chat interactions with documents using various LLMs, multi-user support, and no-code AI agent building capabilities.
• SmythOS/sre (★173 TypeScript) - SmythOS is a comprehensive operating system designed to build, deploy, and manage intelligent AI agents at scale with a unified SDK and modular architecture.
• a2aproject/A2A (★18015 TypeScript) - Agent2Agent (A2A) is an open protocol that enables secure communication and interoperability between opaque AI agents, facilitating multi-agent collaboration across diverse platforms and ecosystems.
• agentgateway/agentgateway (★219 Rust) - Agentgateway is a high-performance, secure, and multi-tenant agent gateway designed for enterprise-grade deployments with robust MCP-focused features and dynamic configuration support.
• aipotheosis-labs/aci (★4152 Python) - ACI.dev is an open-source platform that enables AI agents to securely access and interact with over 600 integrated tools via a unified Model-Context-Protocol (MCP) server or direct function calls, simplifying authentication and infrastructure for production-ready AI applications.
• cjo4m06/mcp-shrimp-task-manager (★1151 TypeScript) - Shrimp Task Manager is an MCP-based intelligent task management system that converts natural language into structured development tasks with dependency tracking and iterative refinement, enhancing AI Agents' programming workflows through chain-of-thought reasoning and task memory.
• cloudwalk/hermes-mcp (★225 Elixir) - Hermes MCP is a high-performance Elixir SDK offering comprehensive client and server implementations of the Model Context Protocol (MCP) to enable standardized communication between AI applications and external tools.
• danny-avila/LibreChat (★27595 TypeScript) - LibreChat is an open-source enhanced ChatGPT clone that integrates multiple AI models and supports the Model Context Protocol (MCP) for advanced AI assistant features including no-code agents, secure code execution, multimodal interactions, and customizable conversation management.
• google-a2a/A2A (★17251 TypeScript) - Agent2Agent (A2A) is an open protocol that enables secure communication and collaboration between opaque AI agentic applications, facilitating interoperability and complex multi-agent tasks without exposing internal states.
• inclusionAI/AWorld (★322 Python) - AWorld is an open-source framework that utilizes MCP servers to build and run collaborative multi-agent assistance systems, advancing agentic AI through self-improving multi-agent learning.
• joinly-ai/joinly (★135 Python) - Joinly.ai is an open-source middleware platform that enables AI agents to join and actively participate in video meetings using a Model Context Protocol server, supporting real-time interaction and multiple meeting platforms.
• kagent-dev/kagent (★1113 Python) - kagent is a Kubernetes native framework for building, deploying, and managing AI agents with integration as an MCP server, supporting multiple LLM providers and tools as Kubernetes custom resources.
• microsandbox/microsandbox (★2812 Rust) - Microsandbox is a self-hosted, secure sandbox environment that uses hardware-level microVM isolation and built-in MCP support to safely and rapidly run AI-generated or untrusted code with full user control.
• mobile-next/mobile-mcp (★1236 TypeScript) - Mobile Next is a Model Context Protocol server enabling scalable, platform-agnostic mobile automation and development across iOS, Android, emulators, simulators, and physical devices using structured accessibility data and screenshot-based interactions.
• modelscope/agentscope (★7572 Python) - AgentScope is a multi-agent platform that simplifies building LLM-empowered distributed applications with robust fault-tolerance and integration with Model Context Protocol (MCP) Server.
• octelium/octelium (★1695 Go) - Octelium is a free and open-source self-hosted unified zero trust secure access platform supporting remote access VPN, ZTNA, API/AI gateways, PaaS, Kubernetes ingress, and MCP/A2A architectures.
• open-webui/open-webui (★101249 JavaScript) - Open WebUI is a self-hosted, extensible AI platform supporting multiple LLM runners and OpenAI-compatible APIs with advanced features like Retrieval Augmented Generation, model building, and offline deployment.

Media & Creativity

• MiniMax-AI/MiniMax-MCP (★764 Python) - MiniMax-MCP is the official MiniMax Model Context Protocol server enabling MCP clients to interact with advanced AI APIs for text-to-speech, voice cloning, image, and video generation.
• Simon-Kansara/ableton-live-mcp-server (★283 Python) - Ableton Live MCP Server is an MCP protocol-based server that enables communication and control of Ableton Live via OSC for integration with large language models and MCP clients.
• abhiemj/manim-mcp-server (★415 Python) - Manim MCP Server is an MCP server that executes Manim animation scripts and returns generated videos, enabling dynamic animation creation through the Model Context Protocol.
• ahujasid/ableton-mcp (★1739 Python) - AbletonMCP integrates Ableton Live with Claude AI using the Model Context Protocol to enable AI-assisted music production and session control through two-way communication.
• anaisbetts/mcp-youtube (★391 JavaScript) - anaisbetts/mcp-youtube is an MCP server that downloads YouTube subtitles using yt-dlp and connects to claude.ai for video summarization via the Model Context Protocol.
• burningion/video-editing-mcp (★175 Python) - An MCP server interface for Video Jungle that enables video upload, search, and automated editing through natural language prompts and API integration.
• elevenlabs/elevenlabs-mcp (★794 Python) - The official ElevenLabs MCP server enabling MCP clients to access advanced text-to-speech and audio processing capabilities through ElevenLabs' APIs.
• emicklei/melrose (★189 Go) - Melrōse is an interactive tool for programming and performing music melodies using a custom language and MIDI, featuring integration with the Model Context Protocol (MCP) for AI-driven music expression playback.
• evalstate/mcp-hfspace (★323 TypeScript) - mcp-hfspace is an MCP server that enables easy integration of Hugging Face Spaces with Claude Desktop, supporting various AI tasks like image generation, vision, speech, and chat through minimal configuration.
• gyoridavid/short-video-maker (★450 TypeScript) - Short Video Maker is an open-source tool that automates the creation of short-form videos for social media using the Model Context Protocol and a REST API.
• hellokaton/unsplash-mcp-server (★140 Python) - Unsplash MCP Server is an MCP server enabling advanced image search and seamless integration of Unsplash's photo library into applications.
• kimtaeyoon83/mcp-server-youtube-transcript (★254 JavaScript) - An MCP server that enables direct retrieval of transcripts from YouTube videos with multi-language support and robust error handling.
• samuelgursky/davinci-resolve-mcp (★236 Python) - DaVinci Resolve MCP Server is an MCP server that enables AI coding assistants like Cursor and Claude Desktop to control and query DaVinci Resolve through natural language commands.
• varunneal/spotify-mcp (★384 Python) - spotify-mcp is an MCP server that connects large language models like Claude with Spotify, enabling playback control, music search, and playlist management through the Model Context Protocol.
• zcaceres/markdownify-mcp (★1866 TypeScript) - Markdownify MCP Server is an MCP server that converts various file types and web content into Markdown format, enabling easy content sharing and management within the MCP ecosystem.

Finance & Trading

• armorwallet/armor-crypto-mcp (★165 Python) - Armor Crypto MCP is an alpha-stage MCP server that integrates AI agents with the cryptocurrency ecosystem, offering multi-chain wallet management, swaps, strategic trades, and more.
• base/base-mcp (★258 TypeScript) - Base MCP Server is a Model Context Protocol server that provides onchain tools for AI applications to interact with the Base network and Coinbase API, enabling advanced blockchain operations and financial transactions.
• caterpillardev/Sui-AI-Agent-Kit (★144 TypeScript) - Sui AI Agent Kit is a toolkit implementing the Model Context Protocol to enable AI agents to seamlessly interact with multiple DeFi protocols on the Sui blockchain for automated and sophisticated decentralized finance operations.
• ferdousbhai/investor-agent (★208 Python) - Investor-agent is a Model Context Protocol server delivering comprehensive financial analysis and market data to large language models for advanced investment insights and trading capabilities.
• financial-datasets/mcp-server (★400 Python) - An MCP server that enables AI assistants to access comprehensive stock market and cryptocurrency data from Financial Datasets via the Model Context Protocol interface.
• goat-sdk/goat (★755 TypeScript) - GOAT is a comprehensive agentic finance toolkit enabling AI agents to autonomously perform financial activities using blockchain, cryptocurrencies, wallets, and supports the Model Context Protocol (MCP) along with other agent frameworks.
• longportapp/openapi (★254 Rust) - LongPort OpenAPI SDK provides programmatic trading and quote interfaces with real-time data and includes an MCP server implementation for advanced investment strategy development.
• razorpay/razorpay-mcp-server (★195 Go) - Razorpay MCP Server is an official Model Context Protocol server that enables advanced payment processing and automation through Razorpay's APIs for developers and AI tools.
• stripe/agent-toolkit (★871 TypeScript) - The Stripe Agent Toolkit is a library that integrates Stripe's API into various agent frameworks and the Model Context Protocol (MCP) to enable seamless payment and billing automation in intelligent agent workflows.
• wshobson/mcp-trader (★162 Python) - MCP Trader is a Model Context Protocol server offering advanced technical analysis and trading tools for stock and cryptocurrency traders, integrating multiple financial metrics and risk management features.

Other MCP Servers

• DMontgomery40/deepseek-mcp-server (★250 JavaScript) - DeepSeek MCP Server is a Model Context Protocol server that enables seamless integration of DeepSeek's advanced language models with MCP-compatible applications, supporting multi-turn conversations, automatic model fallback, and extensive configuration options.
• MigoXLab/dingo (★269 JavaScript) - Dingo is a comprehensive AI data quality evaluation tool featuring multiple datasets and evaluation methods, including an experimental Model Context Protocol (MCP) server for advanced integration.
• SecretiveShell/MCP-Bridge (★796 Python) - MCP-Bridge is middleware that enables seamless integration of MCP tools with the OpenAI API, allowing transparent use of MCP tools through an OpenAI-compatible interface.
• TensorBlock/awesome-mcp-servers (★393 ) - A comprehensive curated collection of Model Context Protocol (MCP) servers categorized by functionality, enabling standardized and secure integration of language models with external tools and data sources.
• TuanKiri/weather-mcp-server (★223 Go) - A lightweight Model Context Protocol (MCP) server that enables AI assistants like Claude to retrieve and interpret real-time weather data.
• appcypher/awesome-mcp-servers (★3316 ) - A curated list of Model Context Protocol (MCP) servers that enable AI models to securely interact with local and remote resources through standardized server implementations, enhancing AI capabilities across various domains.
• automation-ai-labs/mcp-link (★474 Go) - MCP Link automates the conversion of any OpenAPI V3 API into a fully compatible MCP Server, enabling seamless integration with AI Agent frameworks without modifying the original APIs.
• baidu-maps/mcp (★304 Python) - Baidu Map MCP Server is an open-source, fully MCP-compliant location-based service platform providing comprehensive geospatial APIs and tools for seamless integration with AI agents and large language models.
• fatwang2/search1api-mcp (★141 TypeScript) - search1api-mcp is an MCP server that provides advanced web and news search functionalities using Search1API, enabling seamless integration with various MCP clients including LibreChat.
• ihor-sokoliuk/mcp-searxng (★135 JavaScript) - mcp-searxng is an MCP server implementation that integrates the SearXNG API to provide advanced web search capabilities within the Model Context Protocol ecosystem.
• isaacphi/mcp-gdrive (★133 TypeScript) - isaacphi/mcp-gdrive is an MCP server that integrates Google Drive and Google Sheets functionalities, enabling file listing, reading, searching, and editing within the Model Context Protocol ecosystem.
• jaw9c/awesome-remote-mcp-servers (★513 ) - A curated list of high-quality remote Model Context Protocol (MCP) servers for developers to discover reliable and production-ready services for AI applications.
• liuyoshio/mcp-compass (★152 JavaScript) - MCP Compass is a discovery and recommendation service that helps users find and utilize the right Model Context Protocol (MCP) servers through natural language queries and real-time updates.
• loopwork/iMCP (★661 Swift) - iMCP is a macOS app that acts as an MCP server, enabling AI clients to securely access and manage personal data services like Messages, Contacts, Calendar, and more through the Model Context Protocol.
• modelcontextprotocol/servers (★57663 JavaScript) - The Model Context Protocol Servers repository offers reference implementations and third-party integrations that demonstrate how MCP enables Large Language Models to securely access and interact with diverse tools and data sources.
• nickclyde/duckduckgo-mcp-server (★272 Python) - DuckDuckGo MCP Server is an MCP server that provides optimized web search and content fetching through DuckDuckGo for large language model consumption and integration with Claude Desktop.
• nspady/google-calendar-mcp (★423 TypeScript) - Google Calendar MCP Server is an MCP server that enables AI assistants to manage Google Calendar events through a standardized interface with advanced features like smart scheduling, multi-calendar support, and event import from images.
• openbnb-org/mcp-server-airbnb (★218 JavaScript) - Airbnb MCP Server is an MCP server that enables programmatic search and retrieval of detailed Airbnb listing data without requiring an API key.
• ppl-ai/modelcontextprotocol (★1333 JavaScript) - A Model Context Protocol server connector integrating the Perplexity Sonar API to enable real-time web search and live research capabilities for AI assistants like Claude within the MCP ecosystem.
• pskill9/web-search (★211 JavaScript) - An MCP server that enables free Google web searches by scraping search results and returning structured data without requiring API keys.
• punkpeye/awesome-mcp-servers (★59600 ) - A curated collection of Model Context Protocol (MCP) servers that enable AI models to securely interact with local and remote resources through standardized server implementations.
• pyroprompts/any-chat-completions-mcp (★134 JavaScript) - any-chat-completions-mcp is a TypeScript-based MCP server that integrates any OpenAI SDK compatible chat completion API, enabling seamless multi-model chat interactions through the Model Context Protocol.
• taazkareem/clickup-mcp-server (★258 TypeScript) - ClickUp MCP Server is an MCP server that integrates ClickUp task management with AI applications, enabling AI agents to manage tasks, time tracking, documents, and workspace organization through a standardized protocol.
• tavily-ai/tavily-mcp (★539 JavaScript) - Tavily MCP server is an implementation of the Model Context Protocol that enables AI assistants to access and interact with real-time web data through advanced search, extraction, mapping, and crawling tools.
• wegotdocs/open-mcp (★201 TypeScript) - OpenMCP is an open-source standard and registry for converting web APIs into Model Context Protocol (MCP) servers, enabling efficient integration of APIs with MCP clients like large language models.
• wong2/awesome-mcp-servers (★1896 ) - A curated list of Model Context Protocol (MCP) servers showcasing reference implementations and official production-ready integrations for diverse AI-powered applications.
• zcaceres/fetch-mcp (★473 TypeScript) - Fetch MCP Server is an MCP server that fetches and transforms web content into HTML, JSON, plain text, and Markdown formats on demand.

MCP Clients

CLI Tools

• 3choff/mcp-chatbot (★205 Python) - MCP Chatbot is a CLI-based chatbot demonstrating integration of the Model Context Protocol with dynamic tool discovery and multi-server support compatible with various LLM providers.
• Davidyz/VectorCode (★524 Python) - VectorCode is a code repository indexing tool that integrates with the Model Context Protocol to inject task-relevant context from codebases, enhancing coding LLMs' search and retrieval capabilities.
• JohanLi233/Viby (★167 Python) - Viby is a terminal-based AI agent leveraging the Model Context Protocol to provide intelligent, context-aware assistance for coding, shell commands, and information retrieval.
• JohanLi233/viby (★166 Python) - Viby is a terminal-based AI agent that uses the Model Context Protocol to provide intelligent, context-aware assistance for tasks like shell command generation, natural conversations, and smart tool discovery.
• adhikasp/mcp-client-cli (★582 Python) - mcp-client-cli is a command-line interface tool that enables users to run LLM prompts and interact with Model Context Protocol (MCP) compatible servers from the terminal.
• av/harbor (★1897 Python) - Harbor is a containerized toolkit that enables effortless deployment and management of local large language model backends, frontends, and services with integrated support for the Model Context Protocol ecosystem.
• chrishayuk/mcp-cli (★1379 Python) - MCP CLI is a versatile and feature-rich command-line interface for interacting with Model Context Protocol servers, supporting multiple LLM providers, operational modes, and advanced conversation and tool management.
• eugeneyan/news-agents (★279 Python) - News Agents is a terminal-based multi-agent news aggregation and summarization system that uses Model Context Protocol (MCP), Amazon Q, and tmux to fetch and summarize news from various sources in parallel.
• f/mcptools (★971 Go) - MCP Tools is a comprehensive command-line interface for discovering, calling, and managing tools, resources, and prompts on Model Context Protocol (MCP) servers with support for multiple transport methods and output formats.
• ggozad/oterm (★2024 Python) - Oterm is a versatile terminal client for Ollama that supports Model Context Protocol tools and prompts, enabling customizable and persistent AI chat sessions across multiple platforms.
• gitkraken/gk-cli (★235 ) - GitKraken CLI is a cross-platform command-line tool leveraging the Model Context Protocol to manage multiple Git repositories and work items with AI-powered commit and pull request generation, integrating deeply with Git, GitHub, and Jira.
• hyperb1iss/droidmind (★181 Python) - DroidMind is a powerful tool that uses the Model Context Protocol to enable AI assistants to securely control, analyze, and manage Android devices through natural language commands.
• luohy15/y-cli (★166 Python) - y-cli is a terminal-based chat application that supports AI conversations with multiple bot configurations and integrates the Model Context Protocol (MCP) for enhanced client-server communication.
• mattzcarey/shippie (★2189 TypeScript) - Shippie is an AI-powered code review agent that integrates Large Language Models into CI/CD pipelines and functions as a Model Context Protocol client for enhanced integration with external tools.
• michaellatman/mcp-get (★441 TypeScript) - mcp-get is a command-line tool that simplifies discovering, installing, and managing Model Context Protocol (MCP) servers to connect Large Language Models with external data sources and tools.
• pathintegral-institute/mcpm.sh (★643 Python) - MCPM is an open-source CLI tool and service for managing Model Context Protocol (MCP) servers, enabling easy configuration, profile grouping, server discovery, and advanced routing with shared sessions across multiple clients.
• sigoden/llm-functions (★580 Shell) - LLM Functions is a platform that enables easy creation and integration of custom LLM tools and agents using function calling with Bash, JavaScript, and Python, supporting Model Context Protocol for enhanced interoperability.
• strands-agents/agent-builder (★179 Python) - Strands Agent Builder is an interactive, model-driven toolkit for building, testing, and extending custom AI agents with integrated knowledge base support and advanced model configurations.
• wong2/mcp-cli (★350 JavaScript) - mcp-cli is a command-line interface tool for securely inspecting, interacting with, and managing Model Context Protocol (MCP) servers and their resources.
• yamadashy/repomix (★17401 TypeScript) - Repomix is a tool that packs entire code repositories into single, AI-friendly files optimized for feeding Large Language Models and other AI tools, with features for token counting, security, and customization.

Desktop & Mobile Clients

• AI-QL/chat-mcp (★231 HTML) - AI-QL/chat-mcp is a cross-platform desktop chat application leveraging the Model Context Protocol (MCP) to interface seamlessly with various Large Language Models for testing and development purposes.
• AI-QL/tuui (★411 TypeScript) - TUUI is a desktop client application that accelerates AI adoption by integrating and orchestrating cross-vendor LLM APIs through the Model Context Protocol (MCP).
• BigSweetPotatoStudio/HyperChat (★625 TypeScript) - HyperChat is an open-source, multi-platform AI chat client that fully supports the Model Context Protocol (MCP) and integrates various large language model APIs to provide a versatile and productivity-enhanced chat experience.
• ChatGPTNextWeb/NextChat (★84032 TypeScript) - NextChat is a lightweight, privacy-focused AI assistant platform supporting multiple AI models and operating systems, with Model Context Protocol (MCP) support for enhanced AI interactions.
• CherryHQ/cherry-studio (★29476 TypeScript) - Cherry Studio is a cross-platform desktop client supporting multiple LLM providers and featuring an MCP server, AI assistants, document processing, and practical AI tools for enhanced user experience.
• Lucassssss/eechat (★215 JavaScript) - eechat is a secure and efficient local AI chat application featuring Model Context Protocol (MCP) support for seamless integration, management, and invocation of AI tools, enhancing AI assistant capabilities with extensibility and personalization.
• NitroRCr/AIaW (★1167 Vue) - AI as Workspace (AIaW) is a full-featured, cross-platform AI client supporting multiple AI providers and the Model Context Protocol (MCP) to enhance user productivity and experience with large language models.
• Toolbase-AI/toolbase (★151 TypeScript) - Toolbase is a desktop application powered by the Model Context Protocol (MCP) that enables easy discovery, installation, and management of tools and plugins for Claude and other AI platforms.
• daodao97/chatmcp (★1798 Dart) - ChatMCP is a cross-platform AI chat client that implements the Model Context Protocol (MCP) and supports multiple large language models for enhanced AI interactions across various platforms.
• fleuristes/fleur (★491 TypeScript) - Fleur is a desktop app marketplace for discovering, installing, and managing Model Context Protocol (MCP) apps for Claude Desktop and Cursor, designed for both non-technical users and developers.
• mcp-router/mcp-router (★144 TypeScript) - MCP Router is a secure, cross-platform desktop application for centralized management and monitoring of multiple Model Context Protocol (MCP) servers with advanced AI agent integration and detailed logging.
• mediar-ai/screenpipe (★15200 TypeScript) - Screenpipe is an open-source AI app store that records 24/7 desktop and microphone activity locally to provide rich context for building and monetizing AI-powered desktop applications.
• milisp/mcp-linker (★131 TypeScript) - MCP Linker is a cross-platform Tauri GUI application that enables one-click setup, management, and synchronization of MCP servers across multiple AI clients, enhancing usability within the Model Context Protocol ecosystem.
• nanbingxyz/5ire (★4040 TypeScript) - 5ire is a cross-platform desktop AI assistant and MCP client that integrates with major AI providers and supports local knowledge bases and tools via MCP servers for enhanced AI functionality.
• nbonamy/witsy (★1258 TypeScript) - Witsy is a versatile desktop AI assistant and universal MCP client that integrates multiple LLM providers to deliver advanced AI functionalities including chat, vision, text-to-image, and voice interaction using the Model Context Protocol.
• pluveto/daan (★328 TypeScript) - Daan is a lightweight and customizable LLM client that integrates the Model Context Protocol (MCP) to enhance AI interactions with external tools and knowledge, featuring miniapps, character customization, and flexible model support.
• punkpeye/awesome-mcp-clients (★3998 ) - A curated collection of production-ready and experimental Model Context Protocol (MCP) clients enabling secure AI model interactions with local and remote resources through standardized implementations.
• rikkahub/rikkahub (★928 Kotlin) - RikkaHub is a native Android chat client app supporting multiple large language model providers with Model Context Protocol support, multimodal input, and advanced customization features.
• runebookai/tome (★295 Svelte) - Tome is a user-friendly desktop application that enables easy connection, management, and interaction with local and remote large language models through Model Context Protocol servers, simplifying AI integration and customization for all users.
• zueai/mcp-manager (★241 TypeScript) - MCP Manager for Claude Desktop is a MacOS application that provides an easy-to-use interface to manage Model Context Protocol servers, enabling secure and efficient access to various private data sources and APIs for the Claude AI.

IDE Extensions & Code Assistants

• 21st-dev/magic-mcp (★2779 TypeScript) - 21st-dev/magic-mcp is an AI-driven Magic Component Platform server that enables developers to create modern UI components instantly through natural language commands within popular IDEs using the Model Context Protocol.
• CoderGamester/mcp-unity (★713 C#) - MCP Unity is an implementation of the Model Context Protocol that integrates the Unity Editor with AI model clients, enabling AI-driven interactions and automation within Unity projects.
• VikashLoomba/copilot-mcp (★389 TypeScript) - A VSCode extension that integrates MCP servers with GitHub Copilot Chat to provide seamless access to MCP tools and enhance AI-assisted coding workflows.
• cline/cline (★46932 TypeScript) - Cline is an autonomous AI coding assistant integrated into IDEs that uses the Model Context Protocol to safely create and edit files, execute terminal commands, and interact with web applications with user approval at every step.
• ezyang/codemcp (★1469 Python) - codemcp is an AI-powered coding assistant that integrates with Claude Desktop via the Model Context Protocol to enable direct codebase editing, testing, and version-controlled changes for efficient pair programming.
• nrwl/nx-console (★1365 TypeScript) - Nx Console is a user interface tool for Nx and Lerna monorepos that enhances developer productivity with visual workflows, AI-powered context via an MCP server, and deep integration with popular code editors.
• opensumi/core (★3453 TypeScript) - OpenSumi is a framework that enables rapid development of AI Native IDE products by acting as an MCP client supporting Model Context Protocol tools through an MCP server.
• ravitemer/mcphub.nvim (★1271 Lua) - MCP Hub is a Neovim plugin that integrates and manages MCP servers, providing centralized configuration, interactive testing, and deep integration with chat plugins to enhance LLM workflows.

Agent Orchestration Platforms

• Abiorh001/mcp_omni_connect (★143 Python) - MCPOmni Connect is a universal CLI client and intelligent AI agent system that connects to multiple Model Context Protocol (MCP) servers, enabling advanced autonomous task execution, tool orchestration, and resource management across diverse AI models and transport protocols within the MCP ecosystem.
• Azure-Samples/azure-ai-travel-agents (★235 TypeScript) - Azure AI Travel Agents is an enterprise application that leverages multiple AI agents orchestrated via the Model Context Protocol (MCP) to enhance travel agency operations with scalable, cloud-native AI services.
• Ejb503/multimodal-mcp-client (★188 TypeScript) - A modern voice-controlled AI client leveraging Model Control Protocol (MCP) and Google Gemini to enable multimodal, voice-first AI workflows and extensible AI orchestration.
• Onelevenvy/flock (★905 TypeScript) - Flock is a workflow-based low-code platform for rapidly building chatbots, RAG applications, and coordinating multi-agent teams with integrated support for Model Context Protocol (MCP) tools.
• block/goose (★15453 Rust) - Goose is an open-source, extensible AI agent that autonomously automates complex software engineering tasks and integrates seamlessly with Model Context Protocol (MCP) servers.
• dcSpark/shinkai-local-ai-agents (★276 TypeScript) - Shinkai is an open-source platform that enables quick creation of collaborative AI agents supporting Model Context Protocol, local and remote AI, and crypto payments through a no-code interface.
• evilsocket/nerve (★1092 Python) - Nerve is a powerful Agent Development Kit for building, running, evaluating, and orchestrating LLM-based agents with native support for the Model Context Protocol (MCP) using declarative YAML and CLI tools.
• google/A2A (★15157 Python) - Agent2Agent (A2A) is an open protocol by Google that enables secure communication and interoperability between diverse AI agents, fostering collaboration and innovation across different frameworks and ecosystems.
• heshengtao/super-agent-party (★131 JavaScript) - Super Agent Party is a next-generation middleware platform that upgrades LLM APIs to advanced Agent APIs with MCP support and enables one-click deployment to social platforms like QQ.
• heurist-network/heurist-agent-framework (★597 Python) - Heurist Agent Framework is a modular AI agent framework supporting multi-platform interaction, advanced reasoning, tool integration, and MCP protocol for building sophisticated AI agents and agents-as-a-service.
• rinadelph/Agent-MCP (★550 Python) - Agent-MCP is a framework enabling coordinated multi-agent AI collaboration through the Model Context Protocol, facilitating efficient and specialized parallel development workflows in AI software projects.
• truffle-ai/saiki (★165 TypeScript) - Saiki is a customizable AI agent runtime that leverages the Model Context Protocol (MCP) to enable natural language control and orchestration of computers, applications, and services through multiple interfaces including CLI and web UI.

Domain-Specific Integrations

• cohnen/mcp-google-ads (★166 Python) - An MCP tool that integrates Google Ads with Claude AI and Cursor, enabling natural language conversation-based analysis and management of advertising data including campaigns, keywords, and budgets.
• infiolab/infio-copilot (★356 TypeScript) - Infio-Copilot is an AI assistant plugin for Obsidian that offers smart autocomplete, interactive chat with notes, and supports Model Context Protocol integration to enhance note-taking and knowledge management.
• jjsantos01/qgis_mcp (★555 Python) - QGISMCP integrates the Model Context Protocol with QGIS Desktop to enable AI-driven control and automation of GIS projects through Claude AI.
• justinpbarnett/unity-mcp (★2380 C#) - Unity MCP is a bridge that connects the Unity Editor with AI assistants via the Model Context Protocol, enabling natural language control and automation of Unity development tasks.
• mondaycom/mcp (★285 TypeScript) - mondaycom/mcp is an open framework implementing the Model Context Protocol to enable AI agents to securely access and interact with monday.com's work operating system, providing tools and context for intelligent decision-making within workflows.
• prajwalshettydev/UnrealGenAISupport (★216 C++) - UnrealGenAISupport is an Unreal Engine plugin that integrates generative AI models via Model Control Protocol (MCP) to enable automatic blueprint and scene generation, AI-driven game content creation, and control within Unreal Engine 5.5 and above.
• smithery-ai/mcp-obsidian (★972 JavaScript) - mcp-obsidian is a connector that enables MCP clients like Claude Desktop to read and search Obsidian vaults containing Markdown notes, enhancing AI-driven knowledge retrieval.

MCP Frameworks and libraries

Python

• Arize-ai/openinference (★489 Python) - OpenInference is an open-source extension of OpenTelemetry that provides comprehensive tracing and observability for AI applications, including support for the Model Context Protocol (MCP).
• Arize-ai/phoenix (★6232 Jupyter Notebook) - Phoenix is an open-source AI observability platform for experimentation, evaluation, and troubleshooting of large language model applications, supporting multiple frameworks and LLM providers with flexible deployment options.
• GongRzhe/Office-Word-MCP-Server (★339 Python) - Office-Word-MCP-Server is an MCP server that enables AI assistants to create, read, and manipulate Microsoft Word documents through a standardized interface with rich editing capabilities.
• MarkusPfundstein/mcp-gsuite (★390 Python) - mcp-gsuite is an MCP server that integrates Gmail and Google Calendar functionalities through the Model Context Protocol, enabling advanced email and calendar management across multiple Google accounts.
• NicholasGoh/fastapi-mcp-langgraph-template (★434 Python) - A modern, scalable template integrating Model Context Protocol (MCP) and LangGraph for rapid development and deployment of context-aware large language model applications.
• Upsonic/Upsonic (★7560 Python) - Upsonic is a reliability-focused AI agent framework that supports the Model Context Protocol (MCP) to enable trusted, scalable, and production-ready agent workflows with advanced verification and tool integration features.
• a2aproject/a2a-python (★697 Python) - The a2a-python project is the official Python SDK for the Agent2Agent (A2A) Protocol, enabling developers to build and run agentic applications as A2AServers following the A2A Protocol.
• a2aproject/a2a-samples (★400 Jupyter Notebook) - This repository provides code samples and demos for implementing and understanding the Agent2Agent (A2A) Protocol, focusing on secure communication between autonomous agents.
• adhikasp/mcp-git-ingest (★253 Python) - mcp-git-ingest is an MCP server that programmatically reads and visualizes GitHub repository structures and important files, providing tools for directory tree visualization and file content retrieval.
• amidabuddha/console-chat-gpt (★133 Python) - console-chat-gpt is a Python CLI tool that enables seamless interaction with multiple AI chat models, including support for the Model Context Protocol (MCP), providing a customizable and efficient command-line chat experience.
• assafelovic/gpt-researcher (★22193 Python) - GPT Researcher is an autonomous AI agent that conducts deep local and web research on any topic, generating detailed, unbiased reports with citations and supporting integration with the Model Context Protocol (MCP) for enhanced data sourcing.
• awslabs/graphrag-toolkit (★219 Python) - The graphrag-toolkit is a Python toolkit for building graph-enhanced Generative AI applications, featuring BYOKG-RAG for knowledge graph question answering and an MCP server for dynamic tool generation in multi-tenant environments.
• bazinga012/mcp_code_executor (★158 JavaScript) - MCP Code Executor is an MCP server that enables large language models to execute Python code within specified environments, supporting incremental code generation and dynamic environment management.
• cognitivecomputations/dolphin-mcp (★484 Python) - Dolphin MCP is a flexible Python library and CLI tool that enables conversational interaction with multiple Model Context Protocol (MCP) servers using various large language models.
• cyberchitta/llm-context.py (★237 Python) - LLM Context is a tool that enables developers to efficiently share and inject relevant project content into Large Language Model chat interfaces using the Model Context Protocol and customizable rule-based workflows.
• datalayer/jupyter-mcp-server (★454 Python) - Jupyter MCP Server is an MCP server implementation that enables real-time interaction and automation with Jupyter notebooks in JupyterLab environments, compatible with various MCP clients including Claude Desktop AI assistant.
• dodufish/PIXRA (★241 Java) - PIXRA is a reliability-focused AI agent framework that integrates the Model Context Protocol to enable production-ready, scalable, and trustworthy AI workflows with advanced verification and multi-agent capabilities.
• golf-mcp/golf (★642 Python) - Golf is a production-ready framework for building, deploying, and scaling secure MCP servers that power AI agents, featuring automatic component discovery, built-in authentication, observability, debugging, telemetry, and runtime management.
• google-a2a/a2a-python (★530 Python) - Official Python SDK for building and running agentic applications as A2AServers following the Agent2Agent (A2A) Protocol.
• haris-musa/excel-mcp-server (★1360 Python) - An MCP server enabling AI-driven creation, reading, and modification of Excel files without requiring Microsoft Excel installation, supporting both local and remote use through stdio and SSE transport modes.
• heshengtao/comfyui_LLM_party (★1773 Python) - ComfyUI LLM Party is a versatile framework integrating multiple LLMs and MCP server support within ComfyUI to build customizable LLM workflows and AI assistants with social app integration and advanced multi-agent interactions.
• jlowin/fastmcp (★13930 Python) - FastMCP is a Python framework that simplifies building Model Context Protocol (MCP) servers and clients by providing a high-level, Pythonic interface to expose data and functionality to large language models efficiently.
• keli-wen/mcp_chatbot (★162 Python) - A versatile chatbot implementation that integrates customized LLMs with external tools through the Model Context Protocol (MCP), supporting terminal and Streamlit interfaces.
• lamaalrajih/kicad-mcp (★152 Python) - KiCad MCP Server is a cross-platform Model Context Protocol server that enables advanced management and analysis of KiCad PCB projects through MCP-compliant clients using natural language and programmatic interactions.
• lastmile-ai/mcp-agent (★6127 Python) - mcp-agent is a lightweight, composable framework for building AI agents and orchestrating multi-agent systems using the Model Context Protocol in a model-agnostic way.
• lemonade-sdk/lemonade (★170 Python) - Lemonade SDK is a toolkit for serving, benchmarking, and deploying large language models locally with NPU and GPU acceleration, supporting multiple frameworks and providing APIs and CLI tools for integration and evaluation.
• mcp-use/mcp-use (★4136 Python) - mcp-use is an open-source client library that enables easy connection of any tool-capable LLM to MCP servers for building custom agents with diverse tool access.
• microsoft/markitdown (★59841 Python) - MarkItDown is a Python tool that converts various file formats into Markdown and integrates with LLM applications via an MCP server for enhanced text analysis and document processing.
• modelcontextprotocol/python-sdk (★15602 Python) - The official Python SDK for the Model Context Protocol (MCP) enabling developers to build standardized MCP servers and clients for LLM context and interaction.
• mozilla-ai/any-agent (★553 Python) - any-agent is a unified interface for using and evaluating multiple AI agent frameworks, supporting integration with Model Context Protocol tools and multi-agent systems.
• mshojaei77/ReActMCP (★140 Python) - ReActMCP Web Search is an MCP client that integrates real-time web search capabilities into AI assistants using the Exa API, providing Markdown-formatted search results for enhanced AI responses.
• open-strategy-partners/osp_marketing_tools (★196 Python) - osp_marketing_tools is an MCP server providing advanced marketing and writing tools based on Open Strategy Partners' methodologies for technical marketing content creation, optimization, and product positioning, compatible with any MCP-supporting LLM client.
• reading-plus-ai/mcp-server-data-exploration (★416 Python) - MCP Server for Data Exploration is an interactive tool leveraging the Model Context Protocol to transform complex datasets into actionable insights through CSV loading and Python script execution.
• rectalogic/langchain-mcp (★192 Python) - langchain-mcp provides Model Context Protocol (MCP) tool support for the LangChain framework, enabling integration of MCP-compliant tools to enhance language model applications.
• sidharthrajaram/mcp-sse (★286 Python) - An SSE-based implementation pattern for Model Context Protocol (MCP) clients and servers enabling decoupled, cloud-native client-server communication.
• strands-agents/sdk-python (★1894 Python) - Strands Agents is a Python SDK that enables building and running AI agents using a model-driven approach with native support for Model Context Protocol (MCP) servers and multiple AI model providers.
• strands-agents/tools (★363 Python) - Strands Agents Tools is a versatile toolkit that equips AI agents with diverse capabilities through a model-driven approach, enabling them to perform complex tasks with minimal code.
• tadata-org/fastapi_mcp (★6350 Python) - FastAPI-MCP is a tool that exposes FastAPI endpoints as Model Context Protocol (MCP) tools with built-in authentication, preserving schemas and documentation, and supporting flexible deployment using FastAPI's native ASGI interface.
• taylorwilsdon/google_workspace_mcp (★221 Python) - A high-performance MCP server enabling full natural language control and AI assistant integration with all major Google Workspace services including Calendar, Gmail, Drive, Docs, Sheets, Slides, Forms, and Chat.
• themanojdesai/python-a2a (★785 Python) - Python A2A is a production-ready Python library implementing Google's Agent-to-Agent protocol with full Model Context Protocol integration, enabling seamless communication and collaboration between interoperable AI agents.
• tuanle96/mcp-odoo (★162 Python) - An MCP server implementation that integrates AI assistants with Odoo ERP systems, enabling interaction with Odoo data and functionality through the Model Context Protocol.
• utensils/mcp-nixos (★169 Python) - MCP-NixOS is a Model Context Protocol server that delivers accurate, real-time NixOS package and configuration data to AI assistants, preventing hallucinations and ensuring reliable information access.
• vivekVells/mcp-pandoc (★296 Python) - mcp-pandoc is an MCP server that enables seamless document format conversion across multiple formats using pandoc within the Model Context Protocol ecosystem.
• vortezwohl/Autono (★208 Python) - Autono is a ReAct-based highly robust autonomous agent framework that supports adaptive decision making, multi-agent collaboration, and integration with the Model Context Protocol (MCP) for flexible and efficient task execution.
• xing5/mcp-google-sheets (★227 Python) - mcp-google-sheets is a Python-based MCP server that enables AI-driven spreadsheet creation and manipulation by integrating Google Sheets and Drive APIs for use with MCP-compatible clients.

TypeScript

• 3dify-project/dify-mcp-client (★139 Python) - dify-mcp-client is an MCP Client plugin for the Dify platform that enables ReAct Agent nodes to connect to multiple MCP servers, facilitating advanced agent strategies using the Model Context Protocol.
• Axarb/NFTIAI (★232 TypeScript) - NFTI AI is a Web3-native protocol leveraging MCP to tokenize, manage, and deploy AI agents and virtual IPs as NFTs with real-world asset integration, enabling digital sovereignty across multiple blockchains.
• QuantGeekDev/mcp-framework (★759 TypeScript) - MCP Framework is a TypeScript-based framework that simplifies building Model Context Protocol (MCP) servers with features like automatic discovery, multiple transport support, built-in authentication, and comprehensive validation tools.
• Shopify/dev-mcp (★386 TypeScript) - Shopify Dev MCP Server is a Model Context Protocol server that enables interaction with Shopify Dev by providing tools to search documentation and access the Shopify Admin GraphQL schema.
• TencentEdgeOne/edgeone-pages-mcp (★187 HTML) - EdgeOne Pages MCP is an MCP service that enables rapid deployment of HTML content to Tencent's EdgeOne Pages platform, providing publicly accessible URLs for fast edge delivery.
• ThinkInAIXYZ/deepchat (★3591 TypeScript) - DeepChat is an open-source AI chat platform that unifies multiple large language models with advanced search enhancement and Model Context Protocol (MCP) support for tool integration and code execution.
• VoltAgent/voltagent (★2328 TypeScript) - VoltAgent is an open-source TypeScript framework for building and orchestrating autonomous AI agents with support for the Model Context Protocol (MCP) to enable standardized tool interactions and scalable multi-agent systems.
• ZubeidHendricks/youtube-mcp-server (★250 TypeScript) - YouTube MCP Server is an MCP server implementation that enables AI language models to interact with YouTube content for video, channel, and playlist management through a standardized interface.
• activepieces/activepieces (★15623 TypeScript) - Activepieces is an open-source AI automation platform providing an extensible MCP toolkit and over 280 MCP servers for AI agents, designed for both technical and non-technical users.
• antfu/nuxt-mcp (★703 TypeScript) - antfu/nuxt-mcp is an experimental MCP server project that adds Model Context Protocol support to Vite and Nuxt applications, enhancing AI model understanding of these frontend frameworks.
• cgoinglove/mcp-client-chatbot (★324 TypeScript) - MCP Client Chatbot is an open-source AI chatbot interface that integrates multiple AI providers and external tools via the Model Context Protocol, focusing on local execution and user control for an intuitive chat experience.
• exa-labs/exa-mcp-server (★1796 TypeScript) - Exa MCP Server is a Model Context Protocol server that enables AI assistants like Claude to perform real-time web searches using the Exa AI Search API with multiple specialized search tools.
• idosal/mcp-ui (★383 TypeScript) - mcp-ui is a TypeScript SDK that enhances the Model Context Protocol by enabling rich, interactive UI components through server-generated HtmlResourceBlocks and client-side React rendering, facilitating dynamic AI interactions.
• jacksteamdev/obsidian-mcp-tools (★212 TypeScript) - MCP Tools for Obsidian is a plugin and local server that enable secure AI integrations with Obsidian vaults via the Model Context Protocol, providing semantic search, template execution, and controlled vault access for AI applications like Claude Desktop.
• lobehub/lobe-chat (★63098 TypeScript) - Lobe Chat is an open-source, modern AI chat framework supporting multiple AI providers, multi-modal features including MCP, and advanced conversation management with one-click private deployment options.
• mario-andreschak/FLUJO (★503 TypeScript) - FLUJO is an open-source platform that integrates Model-Context-Protocol (MCP) server management, multi-model AI workflows, and secure API key handling into a unified workflow orchestration and chat interface environment.
• mcpdotdirect/evm-mcp-server (★287 TypeScript) - EVM MCP Server is a Model Context Protocol server that enables AI agents to interact with multiple EVM-compatible blockchains through a unified interface, supporting extensive blockchain services including smart contract interactions, token transfers, and ENS name resolution.
• metatool-ai/metamcp (★624 TypeScript) - MetaMCP is a proxy server that aggregates multiple MCP servers into a unified MCP server endpoint, applies middleware, and hosts these endpoints for seamless integration with MCP clients.
• metatool-ai/metatool-app (★514 TypeScript) - MetaMCP is a unified middleware MCP server and GUI application that aggregates multiple MCP servers into a single interface, enabling efficient management, middleware application, and enhanced inspection of MCP servers and clients.
• modelcontextprotocol/typescript-sdk (★8232 TypeScript) - Official TypeScript SDK for building and interacting with Model Context Protocol (MCP) servers and clients, enabling standardized context provision for large language models.
• modelcontextprotocol/use-mcp (★787 TypeScript) - use-mcp is a lightweight React hook that simplifies connecting to Model Context Protocol (MCP) servers by managing authentication, connection states, and tool invocation for AI applications.
• nerding-io/n8n-nodes-mcp (★2099 TypeScript) - An n8n custom node that enables interaction with Model Context Protocol (MCP) servers, allowing AI-driven workflows to access and execute external tools and data sources through MCP.
• punkpeye/fastmcp (★2016 TypeScript) - FastMCP is a TypeScript framework that simplifies building Model Context Protocol (MCP) servers by handling client sessions, multiple content types, real-time updates, and flexible tool definitions using standard schema validation libraries.
• rekog-labs/MCP-Nest (★305 TypeScript) - A NestJS module that enables effortless creation of Model Context Protocol (MCP) servers to expose AI tools, resources, and prompts with support for multiple transport types and authentication.
• samanhappy/mcphub (★682 TypeScript) - MCPHub is a unified management platform that aggregates multiple Model Context Protocol (MCP) servers into streamable HTTP endpoints, providing centralized control, real-time monitoring, secure access, and intelligent tool discovery for efficient AI tool integration.
• sendaifun/solana-agent-kit (★1423 TypeScript) - Solana Agent Kit is an open-source toolkit that enables AI agents to autonomously perform a wide range of actions on Solana blockchain protocols, integrating AI models with decentralized finance, NFTs, and cross-chain operations.
• srbhptl39/MCP-SuperAssistant (★1412 TypeScript) - MCP SuperAssistant is a browser extension that integrates the Model Context Protocol with multiple AI platforms, enabling execution of MCP tools and enhancing AI conversations with real-time data and tool results.
• ssut/Remote-MCP (★188 TypeScript) - Remote-MCP is a type-safe, bidirectional solution enabling remote communication and centralized management of Model Context Protocol (MCP) servers, providing immediate remote MCP access before official support is available.
• tevonsb/homeassistant-mcp (★347 TypeScript) - A Model Context Protocol (MCP) server for Home Assistant that enables natural language control and real-time management of smart home devices through integration with Language Learning Models (LLMs).
• ttommyth/interactive-mcp (★245 TypeScript) - interactive-mcp is a local MCP server that enables interactive prompts, notifications, and chat sessions between large language models and users on their local machines.
• udecode/plate-playground-template (★144 TypeScript) - A modern Next.js 15 template integrating the Plate AI editor with Model Context Protocol (MCP) for building AI-enhanced rich text editing applications.
• vercel-labs/mcp-for-next.js (★217 JavaScript) - An example Next.js MCP server implementation using @vercel/mcp-adapter for integrating Model Context Protocol functionality into Next.js applications, optimized for deployment on Vercel.
• vercel/mcp-adapter (★189 TypeScript) - A Vercel adapter that enables easy deployment of Model Context Protocol (MCP) servers on Next.js and other frameworks, facilitating real-time communication between applications and AI models.
• wong2/litemcp (★178 TypeScript) - LiteMCP is a TypeScript framework that provides an elegant and structured way to build MCP servers with support for tools, resources, prompts, logging, and SSE transport.
• yuniko-software/minecraft-mcp-server (★131 TypeScript) - Minecraft MCP Server is a bot that uses the Model Context Protocol and Mineflayer API to allow AI models like Claude to control a Minecraft character in real-time through natural language commands.
• zaidmukaddam/scira-mcp-chat (★648 TypeScript) - Scira MCP Chat is an open-source AI chatbot client that leverages the Model Context Protocol to connect with various MCP servers and AI tools, providing a modern and extensible chat experience.
• zcaceres/easy-mcp (★162 TypeScript) - EasyMCP is a TypeScript library that simplifies creating Model Context Protocol (MCP) servers with an easy-to-use Express-like and decorators API, focusing on minimal configuration and strong type safety.

Go

• TBXark/mcp-proxy (★368 Go) - mcp-proxy is an MCP proxy server that aggregates multiple MCP resource servers into a single HTTP server, providing real-time updates and flexible configuration for seamless MCP client integration.
• ankorstore/yokai (★732 Go) - Yokai is a simple, modular, and observable Go framework designed to simplify building production-grade backend applications, including support for Model Context Protocol (MCP) applications.
• gojue/moling (★303 Go) - MoLing is a dependency-free, cross-platform MCP server that acts as a local office AI assistant by enabling system and browser interactions and supporting multiple MCP clients.
• ktr0731/go-mcp (★143 Go) - go-mcp is a type-safe and intuitive Go SDK designed to simplify and enhance the development of Model Context Protocol (MCP) servers with robust features and developer-friendly APIs.
• mark3labs/mcp-filesystem-server (★439 Go) - MCP Filesystem Server is a secure and comprehensive Go-based server implementing the Model Context Protocol to provide controlled access and operations on the local filesystem.
• mark3labs/mcp-go (★6227 Go) - A Go SDK implementing the Model Context Protocol (MCP) to enable seamless integration between LLM applications and external data sources and tools.
• modelcontextprotocol/go-sdk (★556 Go) - The official Go SDK for the Model Context Protocol (MCP) providing tools and APIs to build MCP clients and servers, currently unreleased and maintained in collaboration with Google.

C#

• IvanMurzak/Unity-MCP (★246 C#) - Unity MCP is a plugin and server that bridges Large Language Models with Unity, enabling AI-driven interaction and automation within the Unity Editor through the Model Context Protocol.
• afrise/MCPSharp (★300 C#) - MCPSharp is a .NET library that simplifies building Model Context Protocol (MCP) servers and clients, enabling seamless integration of AI tools and models through a standardized API.
• modelcontextprotocol/csharp-sdk (★2706 C#) - Official C# SDK for the Model Context Protocol enabling .NET applications to implement and interact with MCP clients and servers for standardized integration with Large Language Models.

Kotlin

• joreilly/ClimateTraceKMP (★252 Kotlin) - ClimateTraceKMP is a Kotlin/Compose Multiplatform project that visualizes climate-related emission data from climatetrace.org across multiple platforms including iOS, Android, Desktop, and Web.
• joreilly/PeopleInSpace (★3136 Kotlin) - PeopleInSpace is a Kotlin Multiplatform project showcasing cross-platform UI development and backend integration, including an MCP server module for Model Context Protocol data services.
• modelcontextprotocol/kotlin-sdk (★875 Kotlin) - The MCP Kotlin SDK is a multiplatform toolkit providing client and server implementations to integrate context-aware large language model interactions using the Model Context Protocol with support for standard transports like stdio, SSE, and WebSocket.

Java

• Hexeption/MCP-Reborn (★1255 ) - MCP-Reborn is a Mod Coder Pack for Minecraft that enables creating modded clients and researching Minecraft's code for versions 1.13 to 1.21.6, based on MCPConfig and ForgeGradle by the MinecraftForge team.
• OxideWaveLength/Minecraft-Hack-BaseClient (★316 Java) - A Minecraft 1.8.8 base hacked client built on MCP featuring modular command and module management, GUI elements, and social interaction tools.
• SimplyProgrammer/Minecraft-Deobfuscator3000 (★212 ) - Deobfuscator3000 is a universal tool for decompiling and deobfuscating Minecraft mods using customizable MCP mappings, designed to help modders recover and understand mod source code.
• modelcontextprotocol/java-sdk (★1991 Java) - The MCP Java SDK is the official Java SDK enabling Java applications to interact with AI models and tools through the Model Context Protocol, supporting both synchronous and asynchronous communication and integrating with Spring AI for enhanced functionality.
• quarkiverse/quarkus-mcp-server (★133 Java) - Quarkus MCP Server is a Quarkus extension that enables developers to implement Model Context Protocol server features for seamless integration between LLM applications and external data sources and tools.
• quarkiverse/quarkus-mcp-servers (★148 Java) - This project offers a suite of MCP servers implemented in Quarkus to extend MCP-enabled LLM AI applications by enabling interaction with databases, JVM processes, file systems, container engines, Kubernetes, and external APIs.

PHP

• opgginc/laravel-mcp-server (★252 PHP) - Laravel MCP Server by OP.GG is a Laravel package that implements a secure and scalable Model Context Protocol server using Server-Sent Events (SSE) transport for real-time communication and enterprise-grade security.

Ruby

• modelcontextprotocol/ruby-sdk (★281 Ruby) - Official Ruby SDK for implementing Model Context Protocol (MCP) servers and clients with support for JSON-RPC 2.0, tools, prompts, resources, and multiple transport options including Rails and command-line environments.
• yjacquin/fast-mcp (★818 Ruby) - Fast MCP is a Ruby implementation of the Model Context Protocol that simplifies and secures AI model integration with Ruby applications through tools and resources APIs, multiple transport options, and seamless framework support.

Rust

• modelcontextprotocol/rust-sdk (★1631 Rust) - The official Rust SDK for the Model Context Protocol providing asynchronous client and server implementations with Tokio runtime and support for various transport layers.
• paritytech/subxt (★459 Rust) - Subxt is a versatile Rust and WebAssembly library enabling interaction with Substrate-based blockchain nodes through transaction submission, event subscription, storage access, and runtime API calls via static and dynamic interfaces.

Swift

• loopwork-ai/iMCP (★628 Swift) - iMCP is a macOS app that acts as an MCP server, enabling AI clients to securely access and manage personal data services like Calendar, Contacts, Messages, and more through the Model Context Protocol.
• modelcontextprotocol/swift-sdk (★775 Swift) - Official Swift SDK for the Model Context Protocol enabling development of MCP servers and clients with support for multiple transports and real-time communication.

MCP Utilities & Tools

Testing & Debugging

• LSTM-Kirigaya/openmcp-client (★314 HTML) - OpenMCP is an all-in-one VSCode plugin that integrates development, testing, and management tools for Model Context Protocol (MCP) server debugging and large model interaction.
• MCPJam/inspector (★261 TypeScript) - MCPJam Inspector is a developer tool for testing and debugging MCP servers, supporting multiple protocols and LLM interaction, designed to streamline MCP development workflows.
• hyperdrive-eng/mcp-nodejs-debugger (★228 JavaScript) - MCP Node.js Debugger is an MCP server that enables AI assistants like Cursor and Claude Code to debug Node.js applications at runtime by setting breakpoints, inspecting variables, and evaluating code through the Model Context Protocol.
• modelcontextprotocol/inspector (★4638 TypeScript) - MCP Inspector is a developer tool that provides a visual UI and CLI for testing, debugging, and interacting with Model Context Protocol (MCP) servers, enhancing MCP server development workflows.
• modelscope/MCPBench (★144 Python) - MCPBench is an open-source evaluation framework for benchmarking Model Context Protocol (MCP) servers across Web Search, Database Query, and GAIA tasks, measuring accuracy, latency, and token consumption under consistent LLM and agent settings.
• workbackai/mcp-nodejs-debugger (★262 JavaScript) - MCP Node.js Debugger is an MCP server that enables AI coding assistants like Cursor and Claude Code to debug Node.js applications at runtime by setting breakpoints and inspecting runtime state.

Gateways

• API-200/api200 (★221 TypeScript) - API 200 is an open-source API gateway that simplifies third-party API integrations and supports the Model Context Protocol (MCP) for advanced API management.
• AmoyLab/Unla (★1373 Go) - Unla is a lightweight MCP Gateway service that converts existing MCP Servers and APIs into MCP-compliant endpoints through configuration without code changes, supporting Docker and Kubernetes deployments with a management UI.
• IBM/mcp-context-forge (★735 Python) - IBM/mcp-context-forge is a production-grade MCP Gateway that unifies and manages MCP and REST services, providing a secure, scalable, and feature-rich interface for AI clients.
• TheLunarCompany/lunar (★237 Go) - Lunar.dev is an open-source platform providing centralized management, governance, and optimization of third-party API consumption with unified MCP aggregation for AI and application workloads.
• alibaba/higress (★5799 Go) - Higress is a cloud-native AI native API gateway by Alibaba that supports hosting Model Context Protocol (MCP) servers, enabling unified management of AI and LLM APIs with extensible Wasm plugins and enterprise-grade features.
• chatmcp/mcprouter (★272 Go) - mcprouter is an API router and proxy server designed to facilitate efficient communication and interaction with Model Context Protocol (MCP) servers, enabling clients to route and access MCP services through proxying and API requests.
• getdatanaut/openmcp (★284 TypeScript) - OpenMCP is a tool that converts OpenAPI specifications into MCP servers, enabling easy integration and management of multiple MCP tools and servers through a unified configuration.
• lasso-security/mcp-gateway (★217 Python) - MCP Gateway is a plugin-based gateway that orchestrates multiple Model Context Protocol (MCP) servers, providing centralized management, security guardrails, and a unified interface for AI infrastructure.
• lightconetech/mcp-gateway (★132 JavaScript) - MCP Server Gateway is a protocol translator that enables Claude Desktop to communicate with HTTP/SSE-based MCP servers by bridging stdio and HTTP/SSE protocols.
• mcp-ecosystem/mcp-gateway (★760 Go) - MCP Gateway is a lightweight, configuration-driven gateway service that converts existing APIs into MCP protocol-compliant endpoints without code changes, supporting Docker and Kubernetes deployments with a built-in management UI.
• open-webui/mcpo (★2700 Python) - mcpo is a secure and simple proxy server that exposes Model Context Protocol (MCP) tools as OpenAPI-compatible HTTP servers, enabling seamless integration with LLM agents and applications.
• open-webui/openapi-servers (★507 Python) - OpenAPI Tool Servers provides reference implementations and bridging tools to integrate OpenAPI-based tool servers with Model Context Protocol (MCP) servers, enabling secure, standardized APIs for AI applications and workflows.
• sparfenyuk/mcp-proxy (★1232 Python) - mcp-proxy is a proxy server tool that enables communication between MCP servers using stdio and SSE transport protocols, facilitating interoperability within the MCP ecosystem.

MCP Resources & Educational Materials

• Arindam200/awesome-ai-apps (★807 Jupyter Notebook) - A comprehensive collection of practical examples, tutorials, and tools for building powerful LLM-powered AI applications, including chatbots, agents, and workflows, with a focus on the Model Context Protocol (MCP).
• Azure-Samples/AI-Gateway (★651 Jupyter Notebook) - Azure-Samples/AI-Gateway is a project demonstrating the AI Gateway pattern with Azure API Management, integrating AI services like Azure OpenAI and Model Context Protocol to enable secure, efficient, and innovative AI service management and experimentation.
• Puliczek/awesome-mcp-security (★391 ) - Awesome MCP Security is a comprehensive curated resource repository focused on the security aspects, best practices, research, and tools related to the Model Context Protocol (MCP).
• ai-boost/awesome-a2a (★366 ) - A curated collection of resources, tools, and implementations for the Google Agent2Agent (A2A) Protocol enabling secure communication and collaboration between AI agents from different vendors and frameworks.
• aieducations/edumcp (★252 Python) - EDUMCP is an open platform protocol built on the Model Context Protocol (MCP) that enables seamless interoperability among AI models, educational applications, and smart hardware to deliver personalized and interactive learning experiences in education.
• ashishps1/learn-ai-engineering (★1190 ) - A comprehensive curated collection of free resources to learn AI, Machine Learning, Large Language Models, AI Agents, and the Model Context Protocol from scratch.
• cyanheads/model-context-protocol-resources (★227 ) - A comprehensive repository of practical guides, utilities, and server implementations for exploring and learning the Model Context Protocol (MCP), an open standard for connecting AI applications to external tools and data sources.
• gerred/building-an-agentic-system (★183 CSS) - An in-depth practical guide and reference on architecture patterns for building responsive, reliable AI coding agents like Claude Code.
• google-a2a/a2a-samples (★271 Python) - The google-a2a/a2a-samples repository provides practical code samples and demos for implementing and experimenting with the Agent2Agent (A2A) Protocol, facilitating communication between autonomous agents.
• microsoft/mcp-for-beginners (★4392 Python) - An open-source curriculum designed to teach the concepts and fundamentals of the Model Context Protocol (MCP) with practical coding examples in multiple programming languages.
• modelcontextprotocol/modelcontextprotocol (★4403 TypeScript) - The Model Context Protocol project provides a standardized specification and schema for managing model context to enable interoperability in model-driven systems.
• modelcontextprotocol/quickstart-resources (★587 TypeScript) - A repository providing server and client examples from Model Context Protocol tutorials to help users quickly learn and implement MCP.
• multi-modal-ai/multimodal-agents-course (★157 Python) - Kubrick Course is a free, open-source program teaching developers to build advanced MCP multimodal AI agents capable of processing images, text, audio, and video for production-ready AI systems.
• panaversity/learn-agentic-ai (★3090 Jupyter Notebook) - Learn Agentic AI using the Dapr Agentic Cloud Ascent (DACA) design pattern integrating OpenAI Agents SDK, Model Context Protocol (MCP), and Kubernetes to build scalable multi-agent AI systems capable of handling 10 million concurrent agents.
• patchy631/ai-engineering-hub (★13396 Jupyter Notebook) - AI Engineering Hub offers in-depth tutorials and practical resources on Large Language Models, Retrieval-Augmented Generation, and real-world AI agent applications for all skill levels.
• punkpeye/awesome-mcp-devtools (★234 ) - A curated list of developer tools, SDKs, libraries, and utilities for Model Context Protocol (MCP) server development.
• sinanuozdemir/oreilly-ai-agents (★136 Jupyter Notebook) - A comprehensive educational repository and course materials for understanding, implementing, and managing AI agents, with practical examples and integration of Model Context Protocol (MCP).
• sing1ee/a2a-directory (★306 ) - sing1ee/a2a-directory is a comprehensive resource directory for Google's Agent2Agent (A2A) protocol, facilitating secure and asynchronous communication and collaboration between AI agents across diverse platforms and languages.
• strands-agents/samples (★195 Python) - Strands Agents Samples is a repository providing educational and demonstration examples for building AI agents using a model-driven approach with the Strands Agents SDK, supporting learning and experimentation in AI agent development.
• zebbern/claude-code-guide (★785 ) - A comprehensive and detailed guide for Claude Code CLI tool, covering all commands, installation, configuration, and Model Context Protocol (MCP) integration for optimized use.

License