MCP.so
登录
服务器

Paper Search Mcp

@openags

A Model Context Protocol (MCP) server for searching and downloading academic papers from multiple sources, including arXiv, PubMed, bioRxiv, and Sci-Hub (optional). Designed for seamless integration with large language models like Claude Desktop.

概览

What is Paper Search MCP?

Paper Search MCP is a Python-based Model Context Protocol (MCP) server that enables searching and downloading academic papers from multiple sources, including arXiv, PubMed, bioRxiv, and optionally Sci-Hub. Designed for seamless integration with large language models like Claude Desktop, it provides standardized tools for research workflows.

How to use Paper Search MCP?

Install the package with uv add paper-search-mcp or pip install paper-search-mcp, then configure Claude Desktop by adding a JSON entry to the MCP servers configuration file. The server exposes tools such as search_arxiv and download_arxiv that can be invoked through any MCP-compatible client.

Key features of Paper Search MCP

  • Search and download papers from arXiv, PubMed, bioRxiv, and Sci-Hub
  • Returns papers in a consistent dictionary format using the Paper class
  • Asynchronous network requests via httpx for efficient handling
  • Seamless integration with MCP clients for LLM context enhancement
  • Extensible design; easily add new academic platforms

Use cases of Paper Search MCP

  • Quick literature searches combined with AI chat assistants
  • Automated retrieval of paper PDFs for research analysis
  • Building custom research assistants that interact with multiple archives
  • Enabling AI models to fetch relevant academic citations on demand

FAQ from Paper Search MCP

What runtime does Paper Search MCP require?

Python 3.10 or higher is required. The server can be installed via uv or pip.

Where do the papers come from?

Papers are fetched directly from the APIs of arXiv, PubMed, bioRxiv, and optionally Sci-Hub. No local database is used.

Is Sci-Hub required for basic use?

No, Sci-Hub support is optional. The server works with arXiv, PubMed, and bioRxiv without any additional configuration.

How do I integrate it with Claude Desktop?

Add the server configuration to claude_desktop_config.json with the command uv run --directory /path/to/paper-search-mcp -m paper_search_mcp.server.

Does Paper Search MCP require authentication?

No authentication is needed. The server accesses public APIs of the supported academic platforms.

标签

来自「数据与分析」的更多内容