Scholar Search MCP

What it does

Scholar Search MCP connects AI assistants to the world of academic literature. It provides a unified interface to search, retrieve, and analyze academic papers by aggregating data from Semantic Scholar and arXiv, allowing LLMs to perform comprehensive literature reviews and find specific research metadata without leaving the chat.

Tools

• search_papers: Search for academic papers across multiple sources with optional filters for year, venue, and limit.
• get_paper_details: Retrieve comprehensive metadata for a single paper using DOI, arXiv ID, S2 ID, or URL.
• get_paper_citations: Find all papers that cite a specific target paper.
• get_paper_references: Get the list of references cited by a specific paper.
• get_author_info: Fetch detailed profile information for a specific academic author.
• get_author_papers: Retrieve all papers authored by a specific person.
• get_paper_recommendations: Get suggestions for similar academic papers.
• batch_get_papers: Efficiently fetch metadata for up to 500 papers in one call.
• download_arxiv_source: Download and extract the original LaTeX source bundle from arXiv.

Installation

Add the following to your claude_desktop_config.json:

{
  "mcpServers": {
    "scholar-search": {
      "command": "python",
      "args": ["-m", "scholar_search_mcp"],
      "env": {
        "SCHOLAR_SEARCH_ENABLE_SEMANTIC_SCHOLAR": "true",
        "SCHOLAR_SEARCH_ENABLE_ARXIV": "true"
      }
    }
  }
}

Supported hosts

• Claude Desktop
• Cursor