Arxiv

🚀 ArXiv MCP Server

The ArXiv MCP Server enables AI assistants to search and access arXiv academic papers through a simple MCP interface.

The ArXiv MCP Server serves as a bridge between AI assistants and the arXiv research repository. Through the Message Control Protocol (MCP), AI models can programmatically search for and access academic papers.

✨ Features

• 🔎 Paper Search: Filter arXiv papers by date range and category.
• 📄 Paper Access: Download and read paper content.
• 📋 Paper List: View all downloaded papers.
• 🗃️ Local Storage: Save papers locally for quick access.
• 📝 Prompt Sets: A set of prompts for research.

🚀 Quick Start

Installation via Smithery

Use Smithery to automatically install the ArXiv server for the Claude desktop version:

npx -y @smithery/cli install arxiv-mcp-server --client claude

Manual Installation

Install using uv:

uv tool install arxiv-mcp-server

Configure the development environment:

# Clone the repository and set up the development environment
git clone https://github.com/blazickjp/arxiv-mcp-server.git
cd arxiv-mcp-server

# Start the server
npm run dev

🛠️ MCP Configuration

Add the ArXiv server to the configuration file:

{
  "servers": [
    {
      "id": "04dtxi5i5n",
      "name": "ArXiv Server",
      "type": "mcp/arxiv",
      "uri": "http://localhost:3000"
    }
  ]
}

🛠️ Configuration

Configure via environment variables:

🧪 Testing

Run the test suite:

python -m pytest

📄 License

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