
arxiv mcp server
实现 Model Context Protocol (MCP) 服务器,用于与 arXiv API 交互,支持搜索论文、获取详情等功能。
Repository Info
About This Server
实现 Model Context Protocol (MCP) 服务器,用于与 arXiv API 交互,支持搜索论文、获取详情等功能。
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
ArXiv MCP Server
An implementation of the Model Context Protocol (MCP) server for interacting with the arXiv API. This server allows AI assistants to search for scientific papers, retrieve paper details, and discover the latest papers in specific categories.
Features
- Search papers on arXiv with complex queries
- Retrieve papers by ID
- Discover the latest papers in specific categories
- Returns papers as structured MCP resources
Installation
-
Clone this repository:
git clone https://github.com/yourusername/arxiv-mcp-server.git cd arxiv-mcp-server -
Install dependencies:
npm install -
Build the project:
npm run build -
Start the server:
npm start
Project Structure
src/index.ts- Main server implementationpackage.json- Project dependencies and scriptstsconfig.json- TypeScript configuration
Usage with Claude Desktop
-
First, make sure you have the Claude Desktop app installed.
-
Start the ArXiv MCP server:
npm start -
Edit the Claude Desktop configuration file at
~/Library/Application Support/Claude/claude_desktop_config.json(create it if it doesn't exist):{ "mcpServers": { "arxiv": { "command": "node", "args": ["path/to/arxiv-mcp-server/dist/index.js"] } } } -
Restart the Claude Desktop app.
-
You can now ask Claude to use the ArXiv MCP server with queries like:
- "Search for papers about quantum computing on arXiv"
- "Find the latest papers in machine learning"
- "Get details for arXiv paper 2104.12345"
Available Tools
searchArXiv
Search for papers on arXiv with a custom query.
Parameters:
query(required): Search query. Can use prefixes like 'ti:' for title, 'au:' for authormax_results: Maximum number of results to return (default: 10)sort_by: Sort order for results (options: "relevance", "lastUpdatedDate", "submittedDate")sort_order: Sort direction (options: "ascending", "descending")categories: Limit results to specific arXiv categories (e.g., 'cs.AI', 'physics')
getPaperById
Retrieve a specific paper by its arXiv ID.
Parameters:
id(required): The arXiv ID of the paper (e.g., '2101.12345')
getLatestPapers
Get the latest papers from a specific category.
Parameters:
category(required): arXiv category (e.g., 'cs.AI', 'physics.gen-ph')max_results: Maximum number of results to return (default: 10)
License
MIT
Acknowledgments
- Thank you to arXiv for use of its open access interoperability.
- Built with Anthropic's Model Context Protocol.
Quick Start
Clone the repository
git clone https://github.com/ndellamaria/arxiv-mcp-serverInstall dependencies
cd arxiv-mcp-server
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.