scholar-search-mcp

Overview

Scholar Search MCP is a robust MCP server that unifies academic literature search across multiple sources. It provides parallel searching across Semantic Scholar and arXiv with intelligent deduplication by normalized titles. The server offers a comprehensive suite of research tools including paper search, citation tracking, reference retrieval, author profiling, paper recommendations, batch operations, and arXiv source download. Its LLM-friendly outputs make it ideal for downstream reasoning and agent workflows in academic research.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

• search_papers

  Search papers with optional limit, fields, year, venue

  Try:Search for papers about machine learningTry:Find recent papers on quantum computingTry:Show me papers from NeurIPS 2023
• get_paper_details

  Get one paper by DOI, arXiv ID, S2 ID, or URL

  Try:Get details for paper 10.1137/1Try:Fetch information for arXiv:2301.00001Try:Show me details for this paper https://example.com/paper
• get_paper_citations

  Get papers that cite a given paper

  Try:Find papers that cite 'Attention is All You Need'Try:Show me papers that cite this paperTry:Who has referenced this research?
• get_paper_references

  Get references of a given paper

  Try:Show me the references for this paperTry:What papers does this one cite?Try:List the references of this research
• get_author_info

  Get an author profile by ID

  Try:Get information about author 123456Try:Show me details for this researcherTry:Fetch author profile
• get_author_papers

  Get papers by a given author

  Try:Show me papers by this authorTry:What papers has John Doe published?Try:Find all publications by researcher ID
• get_paper_recommendations

  Get similar paper recommendations

  Try:Find similar papers to this oneTry:Show me papers like thisTry:Recommend papers similar to this research
• batch_get_papers

  Batch fetch paper details (up to 500 IDs)

  Try:Get details for these 10 papersTry:Fetch information for multiple papers at onceTry:Batch retrieve paper metadata
• download_arxiv_source

  Download and extract arXiv source bundle

  Try:Download source for arXiv:2301.00001Try:Get the LaTeX source for this paperTry:Extract arXiv source bundle

Comparable tools

Installation

pip install scholar-search-mcp

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

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

FAQ

What is the difference between Semantic Scholar and arXiv searches?

Semantic Scholar provides comprehensive academic paper metadata with citation analysis, while arXiv offers preprint research papers. The MCP server runs both in parallel and deduplicates results by normalized titles.

Do I need API keys to use this server?

No, arXiv works without API keys. Semantic Scholar works with free API key with limited rate limits. Adding a SEMANTIC_SCHOLAR_API_KEY increases rate limits.

Compare scholar-search-mcp with