Blazickjp Arxiv MCP Server

🚀 arXiv MCP Server

Enable AI assistants to search and access arXiv papers through a simple MCP interface.

The arXiv MCP server bridges the gap between AI assistants and the arXiv research repository via the Message Control Protocol (MCP). It allows AI models to programmatically search for and access paper content.

✨ Features

• 🔎 Paper Search: Filter and query arXiv papers using date ranges and categories.
• 📄 Paper Access: Download and read paper content.
• 📋 Paper List: View all downloaded papers.
• 🗃️ Local Storage: Save papers locally for faster access.

🚀 Quick Start

Install using uv:

uv pip install git+https://github.com/blazickjp/arxiv-mcp-server.git

For development:

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

# Create and activate a virtual environment
uv venv
source .venv/bin/activate

# Install with test dependencies
uv pip install -e ".[test]"

🔌 MCP Integration

Add the following to your MCP client configuration file:

{
    "mcpServers": {
        "arxiv-mcp-server": {
            "command": "uv",
            "args": [
                "run",
                "arxiv-mcp-server",
                "--storage-path", "/path/to/paper/storage"
            ]
        }
    }
}

💻 Usage Examples

Basic Usage

The server provides four main tools:

1. Paper Search

Search for papers using filters:

result = await call_tool("search_papers", {
    "query": "transformer architecture",
    "max_results": 10,
    "date_from": "2023-01-01",
    "categories": ["cs.AI", "cs.LG"]
})

2. Paper Download

Download a paper by its arXiv ID:

result = await call_tool("download_paper", {
    "paper_id": "2401.12345"
})

3. List Papers

View all downloaded papers:

result = await call_tool("list_papers", {})

4. Read Paper

Access the content of a downloaded paper:

result = await call_tool("read_paper", {
    "paper_id": "2401.12345"
})

🔧 Configuration

Configure via environment variables:

🧪 Testing

Run the test suite:

python -m pytest

📄 License

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

Developed by [Team Name]. For more information, visit Project Homepage