Arxiv Paper MCP

🚀 🧠 arXiv Research Assistant MCP Server

This project is a server based on the Model Context Protocol (MCP), designed to interact with the vast arXiv.org paper database. It allows clients like Claude AI to efficiently search, explore, and compare arXiv papers through a local server.

🚀 Quick Start

Installation via Smithery

To automatically install the arXiv Research Assistant MCP Server for Claude Desktop via Smithery:

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

Installation from PyPI

uv pip install arxiv-paper-mcp

🔧 Repository Cloning (for Development)

git clone https://github.com/daheepk/arxiv-mcp-server.git
cd arxiv-mcp-server

🔧 Installing Dependencies (for Development)

Install all dependencies in editable mode using uv:

uv pip install -e .

▶️ Running the Server Locally

arxiv-paper-mcp

🔌 Using with Claude

To use this MCP server with Claude, add the following JSON configuration to Claude's MCP settings:

{
  "mcpServers": {
    "arXivPaper": {
      "command": "uv",
      "args": [
        "tool",
        "run",
        "arxiv-paper-mcp"
      ]
    }
  }
}

✨ Features

• 🔍 Keyword-based Paper Search
  Search for arXiv papers using keywords, with support for sorting by relevance or latest updates.

• 📚 Latest Papers by Category
  Specify arXiv classification codes (e.g., cs.AI, math.AP) to get the latest papers in that field.

• 📄 Paper Detail Query
  Use the arXiv ID to obtain detailed metadata: title, authors, abstract, classification, DOI, PDF link, etc.

• 🧑‍🔬 Author-based Paper Search
  Retrieve a list of papers published by a specific author.

• 📊 Trend Analysis (Experimental)
  Get an overview of trends for popular keywords or topics in a category (currently using simulated data).

• 📝 Abstract Prompt Generator
  Dynamically generate prompts to help LLMs more effectively summarize selected papers.

• 🆚 Comparison Prompt Generator
  Provide two paper IDs to generate a structured prompt for comparative content.

🔧 Technical Details

• Python 3.11+
• FastMCP
• uv (for dependency and environment management)
• requests (for API communication)
• xml.etree.ElementTree (for XML response parsing)

📚 Project Structure

arxiv-mcp-server/
├── arxiv_mcp/              # Main package
│   ├── __init__.py
│   ├── app.py              # FastMCP application settings
│   ├── server.py           # Server entry point
│   ├── utils.py            # arXiv API communication logic
│   ├── resources/          # MCP resources (categories, authors, etc.)
│   ├── tools/              # MCP tools (search, detail lookup, trend analysis)
│   └── prompts/            # Prompt templates (summary generation, comparison)
├── pyproject.toml          # Project configuration and dependencies
└── README.md               # This file