Arxiv Paper MCP

🚀 ArXiv Paper MCP

An arXiv-based paper retrieval and content parsing tool. It supports the Model Context Protocol (MCP) standard and provides functions for paper search, PDF link acquisition, and content parsing.

🚀 Quick Start

ArXiv Paper MCP is a powerful tool designed to streamline the process of searching, retrieving, and parsing academic papers from arXiv. It adheres to the Model Context Protocol (MCP), ensuring seamless integration with various AI applications.

✨ Features

• 🔍 Intelligent arXiv Paper Search: Conduct keyword searches to quickly locate papers of interest.
• 🔗 Get PDF Download Links: Obtain direct PDF download links for arXiv papers.
• 📄 Paper Content Parsing: Smartly parse paper content, prioritizing the HTML version and falling back to PDF.
• 🆕 Latest Papers in AI Field: Retrieve the latest updated paper list in the AI field on arXiv today.

📦 Installation

NPX (Recommended)

npx @langgpt/arxiv-paper-mcp

Global Installation

npm install -g @langgpt/arxiv-paper-mcp
arxiv-paper-mcp

📚 Configuration for MCP Clients

Claude Desktop Configuration

Add the following to the Claude Desktop configuration file:

{
  "mcpServers": {
    "arxiv-paper-mcp": {
      "command": "npx",
      "args": ["-y", "@langgpt/arxiv-paper-mcp@latest"]
    }
  }
}

Configuration file locations:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json

Other MCP Clients

For other MCP-supported clients, refer to their documentation for stdio transmission configuration.

💻 Available Tools and Parameters

1. Search Papers

• Tool Name: search_arxiv
• Parameters:
  • query: Search keywords
  • maxResults: Number of papers to return (optional, default is 5)

2. Get PDF Download Links

• Tool Name: get_arxiv_pdf_url
• Parameters:
  • input: arXiv paper URL or arXiv ID (e.g., 2403.15137v1)

3. Parse Paper Content

• Tool Name: parse_paper_content
• Parameters:
  • input: arXiv paper URL or arXiv ID
  • paperInfo: Paper metadata (optional, used for adding paper metadata)

4. Get Recent AI Papers

• Tool Name: get_recent_ai_papers
• Parameters: None

💻 Usage Examples

Basic Usage

1. Search for Papers: Use the search_arxiv tool to search for relevant papers.
2. Get Recent AI Papers: Use the get_recent_ai_papers tool to retrieve the latest AI papers today.
3. Get PDF Links: Use the get_arxiv_pdf_url tool to obtain PDF download links.
4. Parse Paper Content: Use the parse_paper_content tool to get the text content of the paper (prioritize HTML, fall back to PDF).

🔧 Development Guide

Local Development

# Clone the project
git clone https://github.com/yzfly/arxiv-paper-mcp.git
cd arxiv-paper-mcp

# Install dependencies
npm install

# Run in development mode
npm run dev

# Build the project
npm run build

# Run the built version
npm start

Project Structure

arxiv-paper-mcp/
├── src/
│   └── index.ts          # Main server file
├── build/                # Compilation output directory
├── package.json          # Project configuration
├── tsconfig.json         # TypeScript configuration
├── README.md             # Project description
└── LICENSE               # License

🔧 Technical Details

• Node.js >= 18.0.0
• TypeScript - Type-safe JavaScript
• Model Context Protocol - Standardized AI context protocol
• arXiv API - Academic paper data source

🛠️ Troubleshooting

Common Issues

1. Paper Search Failure

Error: Search failed
Solution: Check your network connection and ensure the search keywords are correct.

2. PDF Parsing Failure

Error: PDF parsing failed
Solution: Check if the arXiv ID is correct and ensure the paper exists.

Log Debugging

Enable detailed logs:

DEBUG=arxiv-paper-mcp npx @langgpt/arxiv-paper-mcp

🤝 Contribution Guide

Contributions are welcome! Please follow these steps:

1. Fork the project.
2. Create a feature branch: git checkout -b feature/amazing-feature
3. Commit your changes: git commit -m 'Add amazing feature'
4. Push the branch: git push origin feature/amazing-feature
5. Create a Pull Request.

📄 License

This project is licensed under the MIT License. See the LICENSE file for details.

👨‍💻 Author Information

• Author: yzfly
• Email: yz.liu.me@gmail.com
• GitHub: https://github.com/yzfly

🔗 Related Links

• Model Context Protocol
• arXiv.org
• Claude Desktop

🎉 Support

If you find this project useful, please give it a ⭐!

If you have any questions or suggestions, please contact us through the following channels:

• 📧 Email: yz.liu.me@gmail.com
• 🐛 GitHub Issues: Project Issue Tracking
• 💬 GitHub Discussions: Project Discussion Area