Log inSubmit server
Semantic Scholar MCP logo

Semantic Scholar MCP

by smaniches

Research Semantic Scholar papers, authors, citations, references, snippets, and recommendations through 14 typed MCP tools.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Semantic Scholar MCP

Pick your client, then add it in one click or paste the config.

STDIOPython
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "smaniches-semantic-scholar-mcp": {
      "command": "uvx",
      "args": [
        "s2-mcp-server"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Install not yet sandbox-tested— the server itself is confirmed live (we called its tools/list endpoint). The stdio install command is a separate, ongoing check.

Overview

smaniches/semantic-scholar-mcp connects MCP clients to Semantic Scholar’s index of more than 200 million academic papers. Its 14 typed tools cover paper and author search, identifier-based retrieval, citation and reference traversal, bulk operations, full-text snippets, citation export, and recommendations. Results use Markdown by default, with JSON available for most tools, and the server can run through uvx, pip, Docker, or supported MCP client configurations. Reach for it when an agent needs to discover literature, inspect researchers, follow a citation graph, or generate BibTeX from Semantic Scholar records.

Use cases

  • Search academic literature by topic, year, field, or citation count
  • Trace citations and references from a known paper
  • Find author profiles and verify researcher identity
  • Discover related papers from positive and negative examples
  • Export paper metadata as BibTeX

Key features

  • 14 typed MCP tools for Semantic Scholar
  • Paper and author search with bulk retrieval
  • Citation and reference graph traversal
  • Single- and multi-paper recommendations
  • Full-text snippet search
  • Markdown or JSON research results

Tools14

What Semantic Scholar MCP lets your agent do. Expand a tool for its parameters.

Verified live~5.6k tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 2d ago

Recent health check succeeded.

6/7 checks healthy over the last 80d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 11d ago via OSV.dev · s2-mcp-server (PyPI)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars23Stargazers on the source repository.
Last commit2d agoMost recent push to the default branch.
Tools exposed14Callable tools this server registers over MCP.
Directory activity8 viewsConfig copies, upvotes, and views on AllMCPs.

How Semantic Scholar MCP works

What smaniches/semantic-scholar-mcp does

smaniches/semantic-scholar-mcp exposes Semantic Scholar research data through 14 MCP tools. It works with a corpus of more than 200 million academic papers and provides access to paper metadata, author profiles, citation relationships, recommendations, and full-text search snippets.

Paper workflows include relevance-ranked search, title matching, identifier-based lookup, bulk retrieval, sorted searches, and cursor pagination. Supported paper identifiers include Semantic Scholar IDs, DOI, arXiv, PubMed, and Corpus ID formats. Paper details can include abstracts, authors, venues, publication years, citation counts, TLDRs, open-access PDF links, citations, and references.

Author tools search by name, retrieve profiles, load publications, fetch complete author profiles for a paper, and batch multiple author lookups. Citation export produces BibTeX for a known paper.

How it works

The server communicates with Semantic Scholar through typed MCP tools. Search and profile responses are formatted as Markdown by default; most tools accept response_format='json' when an agent needs structured output. Citation export returns BibTeX text and does not provide a response-format option.

Use semantic_scholar_recommendations with one seed paper, or use semantic_scholar_multi_recommend with positive and negative example papers to steer results. Regular paper search supports boolean operators, quoted phrases, field and publication filters, year ranges, open-access filtering, citation-count filtering, and offset-based paging. Bulk search adds sorting and continuation tokens for larger result sets.

Paper details are cached in memory for five minutes. Requests for citations and references are fetched in parallel, with between one and 100 items per direction. The status tool checks server health, Semantic Scholar connectivity, and API-key status.

Setup and configuration

The quickest launch method is:

bash
uvx s2-mcp-server

The package can also be installed with pip, run from a source checkout, or started from the published container image:

Terminal
pip install s2-mcp-server
docker pull ghcr.io/smaniches/semantic-scholar-mcp:latest

Claude Code can register the stdio server with:

Terminal
claude mcp add semantic-scholar -- uvx s2-mcp-server

No API key is needed to start. Set SEMANTIC_SCHOLAR_API_KEY to use an assigned Semantic Scholar quota and avoid the shared unauthenticated pool. The package requires Python 3.10 or newer.

Tools and capabilities

  • Search papers with filters, boolean syntax, phrases, and paging.
  • Search large or sorted result sets with cursor continuation.
  • Match a single paper from a known title.
  • Retrieve one or many papers by supported identifiers.
  • Traverse citations and references from paper records.
  • Search authors and retrieve individual or batched profiles.
  • Retrieve complete profiles for a paper’s authors.
  • Recommend papers from one or multiple positive and negative examples.
  • Search paper full text for contextual snippets.
  • Export known papers as BibTeX citations.
  • Check API connectivity and key status.

Limitations and notes

Unauthenticated requests are throttled to one request per second; the documented keyed limit is 10 requests per second for applicable requests. Full-text snippet search is heavily rate-limited without an API key. Paper bulk retrieval accepts up to 500 papers, author batches up to 1,000 authors, and individual search pages up to 100 results. Recommendation results accept up to 500 items, with multi-example inputs capped at 100 positive and 100 negative paper IDs.

Unknown paper or author identifiers can produce not-found errors, and malformed identifiers are rejected before a multi-recommendation request. Requests receiving 429, 502, or 503 responses retry automatically with backoff for the supported retrieval and recommendation operations. The release artifacts include SLSA build provenance, PyPI attestations, and a CycloneDX SBOM. The project is licensed under MIT.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Semantic Scholar MCP

smaniches/semantic-scholar-mcp is an MCP server that connects AI clients to Semantic Scholar’s academic literature index. Its main tools search and retrieve papers, inspect authors, traverse citations and references, find recommendations, search full-text snippets, export BibTeX, and check API status across 200M+ papers.

Run `uvx s2-mcp-server` for a direct launch, or install it with `pip install s2-mcp-server`. Docker users can pull `ghcr.io/smaniches/semantic-scholar-mcp:latest`; Claude Code users can register the stdio command with `claude mcp add semantic-scholar -- uvx s2-mcp-server`.

No, an API key is not required to start. Set `SEMANTIC_SCHOLAR_API_KEY` to use an assigned quota and avoid the shared unauthenticated pool. Unkeyed requests are throttled to one request per second, while keyed requests can use the documented 10-request-per-second limit.

Yes, Cursor is named as a supported MCP client. The server also supports standard MCP client configurations through its stdio launch command, including `uvx s2-mcp-server`.

Use `semantic_scholar_search_papers` for relevance-ranked searches with boolean operators, quoted phrases, year, field, publication-type, open-access, and citation-count filters. Use `semantic_scholar_bulk_search` for sorting and cursor pagination, or `semantic_scholar_snippet_search` to search within paper full text.

Related MCP servers

All in Research All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewSemantic Scholar MCP AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/smaniches-semantic-scholar-mcp?style=directory)](https://allmcps.com/mcp/smaniches-semantic-scholar-mcp)
HTML Embed
<a href="https://allmcps.com/mcp/smaniches-semantic-scholar-mcp"><img src="https://allmcps.com/api/badge/smaniches-semantic-scholar-mcp?style=directory" alt="Semantic Scholar MCP on AllMCPs" /></a>