mcp test
一个快速实现的 MCP 服务器和客户端，基于 Langgraph Agent。
Repository Info
About This Server
一个快速实现的 MCP 服务器和客户端，基于 Langgraph Agent。
Model Context Protocol (MCP) - This server can be integrated with AI applications to provide additional context and capabilities, enabling enhanced AI interactions and functionality.
Documentation
Example of a quick MCP Server and MCP Client as Langgraph Agent.
It is recommended to use the dev container
- Run
poetry install - Get AWS credentials loaded. It currently uses the
devprofile to talk to AWS bedrock, but you can change it to whatever yours is named insrc/shared/models.py. - Run
poetry run python src/tools.pyto start the MCP server. - In a new terminal run
poetry run python src/client.pyto start the FastAPI server that runs our Langgraph agent. - Call GET
localhost:8001/testto invoke the agent with a stock prompt.
NOTE
This was originally created to test phoenix MCP traces, but the phoenix code is all commented out for now. This also means there is no need to start the docker compose file right now.
Quick Start
Clone the repository
git clone https://github.com/grey-lovelace/mcp-testInstall dependencies
cd mcp-test
npm installFollow the documentation
Check the repository's README.md file for specific installation and usage instructions.
Repository Details
Recommended MCP Servers
Discord MCP
Enable AI assistants to seamlessly interact with Discord servers, channels, and messages.
Knit MCP
Connect AI agents to 200+ SaaS applications and automate workflows.
Apify MCP Server
Deploy and interact with Apify actors for web scraping and data extraction.
BrowserStack MCP
BrowserStack MCP Server for automated testing across multiple browsers.
Zapier MCP
A Zapier server that provides automation capabilities for various apps.