Semantic Scholar MCP Server

A FastMCP server implementation for the Semantic Scholar API, providing comprehensive access to academic paper data, author information, and citation

Local serverstdioPython

What is the Semantic Scholar MCP server?

Most developer tooling work still happens through a UI a human drives. Semantic Scholar MCP server moves it into the conversation instead. A FastMCP server implementation for the Semantic Scholar API, providing comprehensive access to academic paper data, author information, and citation networks.

The short version

  • Paper Search & Discovery —
  • Full-text search with advanced filtering
  • Title-based paper matching
  • Paper recommendations (single and multi-paper)
  • Batch paper details retrieval
  • Advanced search with ranking strategies

The tools it exposes

The server publishes 14 tools. What each one is for:

  • paper_relevance_search — Search for papers using relevance ranking
  • paper_bulk_search — Bulk paper search with sorting options
  • paper_title_search — Find papers by exact title match
  • paper_details — Get comprehensive details about a specific paper
  • paper_batch_details — Efficiently retrieve details for multiple papers
  • paper_authors — Get the authors associated with a specific paper
  • paper_autocomplete — Get paper title suggestions for a partial query
  • snippet_search — Search within paper snippets and excerpts
  • paper_citations — Get papers that cite a specific paper
  • paper_references — Get papers referenced by a specific paper
  • author_search — Search for authors by name
  • author_details — Get detailed information about an author

What it needs from you

Configuration is passed through the environment: SEMANTIC_SCHOLAR_API_KEY, SEMANTIC_SCHOLAR_HTTP_BRIDGE_HOST. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Getting it running

@smithery/cli on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.

How it compares

Plenty of developer tooling servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Semantic Scholar's toolset — paper_relevance_search, paper_bulk_search, paper_title_search and 11 more — is a fair guide to whether it matches your workflow. It is maintained by YUZongmin; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Semantic Scholar.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
paper_relevance_searchSearch for papers using relevance ranking
paper_bulk_searchBulk paper search with sorting options
paper_title_searchFind papers by exact title match
paper_detailsGet comprehensive details about a specific paper
paper_batch_detailsEfficiently retrieve details for multiple papers
paper_authorsGet the authors associated with a specific paper
paper_autocompleteGet paper title suggestions for a partial query
snippet_searchSearch within paper snippets and excerpts
paper_citationsGet papers that cite a specific paper
paper_referencesGet papers referenced by a specific paper
author_searchSearch for authors by name
author_detailsGet detailed information about an author
author_papersGet papers written by an author
author_batch_detailsGet details for multiple authors

How to install the Semantic Scholar MCP server

{
  "mcpServers": {
    "semantic-scholar-fastmcp": {
      "command": "npx",
      "args": ["-y", "@smithery/cli"],
      "env": {
        "SEMANTIC_SCHOLAR_API_KEY": "your-value",
        "SEMANTIC_SCHOLAR_HTTP_BRIDGE_HOST": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
SEMANTIC_SCHOLAR_API_KEYCredential the server authenticates with.Yes
SEMANTIC_SCHOLAR_HTTP_BRIDGE_HOSTEndpoint or connection string the server talks to.Optional

Example prompts to try

  • Use Semantic Scholar to paper relevance search.
  • Use Semantic Scholar to paper bulk search.
  • Use Semantic Scholar to paper title search.

Frequently asked questions

An API key is optional. Without it, the server uses unauthenticated access with lower rate limits (100 requests per 5 minutes). With an API key, you get higher limits (1 request per second for search, batch, and recommendations; 10 per second for other endpoints).