Skip to main content
Glama
semanticscholar-mcp

semanticscholar-mcp

by dam2452

semanticscholar-mcp

Polski

Semantic Scholar Academic Graph API via MCP.

Table of contents

Related MCP server: Semantic Scholar MCP Server

Tools

Tool

Parameters

Description

search_papers

query, fields, year, venue, fields_of_study, open_access_pdf, min_citation_count, publication_types, limit, offset

Relevance-ranked paper search

search_papers_bulk

query, fields, year, venue, sort, publication_types, fields_of_study, token

Bulk paper search (up to 1000/call, with continuation token)

match_paper_title

query, fields

Find the paper whose title best matches a query

autocomplete_paper

query

Suggest paper title completions

get_paper

paper_id, fields

Details about a single paper

get_papers_batch

paper_ids, fields

Details for up to 500 papers at once

get_paper_authors

paper_id, fields, limit, offset

Authors of a given paper

get_paper_citations

paper_id, fields, limit, offset

Papers that cite a given paper

get_paper_references

paper_id, fields, limit, offset

Papers referenced by a given paper

search_authors

query, fields, limit, offset

Search for authors by name

get_author

author_id, fields

Details about a single author

get_author_papers

author_id, fields, limit, offset

Papers written by a given author

get_authors_batch

author_ids, fields

Details for up to 1000 authors at once

search_snippets

query, paper_ids, fields_of_study, venue, publication_types, insertion_ids, min_citation_count

Search text snippets from paper full texts, abstracts, and titles

All Semantic Scholar API calls are throttled to 1 request per second, cumulative across all tools, per the API's rate limit.

Environment variables

Variable

Required

Description

S2_API_KEY

yes

Semantic Scholar API key, sent as the x-api-key header

Wiring it up

Only requirement: uv (https://docs.astral.sh/uv/). Nothing else to install.

Claude Code

claude mcp add semanticscholar-mcp -e S2_API_KEY=<value> -- uvx --from git+https://github.com/dam2452/semanticscholar-mcp.git semanticscholar-mcp

Claude Desktop / other MCP client

{
  "mcpServers": {
    "semanticscholar-mcp": {
      "command": "uvx",
      "args": ["--from", "git+https://github.com/dam2452/semanticscholar-mcp.git", "semanticscholar-mcp"],
      "env": { "S2_API_KEY": "<value>" }
    }
  }
}

After pushing a new version: uv cache clean and restart the client.

Local run

uv run --directory . semanticscholar-mcp

Tests (manual):

uv run --directory . --with pytest pytest test/

Available Tools

14 tools
autocomplete_paperA

Suggest paper title completions for a partial query string.

Inputs: query (required). Returns: object

get_authorA

Get details about a single author identified by their Semantic Scholar author ID.

Inputs: author_id (required), fields. Returns: object

get_author_papersB

List the papers written by a given author.

Inputs: author_id (required), limit, fields, offset. Returns: object

get_authors_batchB

Get details for up to 1000 authors at once, given a list of author IDs.

Inputs: author_ids (required), fields. Returns: result

get_paperA

Get details about a single paper identified by its Semantic Scholar ID, DOI, arXiv ID, or other supported external ID.

Inputs: paper_id (required), fields. Returns: object

get_paper_authorsB

List the authors of a given paper.

Inputs: paper_id (required), limit, fields, offset. Returns: object

get_paper_citationsB

List the papers that cite a given paper.

Inputs: paper_id (required), limit, fields, offset. Returns: object

get_paper_referencesB

List the papers referenced by a given paper.

Inputs: paper_id (required), limit, fields, offset. Returns: object

get_papers_batchA

Get details for up to 500 papers at once, given a list of paper IDs.

Inputs: paper_ids (required), fields. Returns: result

match_paper_titleB

Find the single paper whose title best matches the given query string.

Inputs: query (required), fields. Returns: object

search_authorsC

Search for authors by name.

Inputs: query (required), limit, fields, offset. Returns: object

search_papersB

Relevance-ranked search for papers matching a text query, with optional filters on year, venue, field of study, publication type, citation count, and open access availability.

Inputs: query (required), year, limit, venue, +6 more. Returns: object

search_papers_bulkA

Bulk paper search returning up to 1000 papers per call without relevance ranking, with a continuation token for paging through larger result sets.

Inputs: sort, year, query, token, +4 more. Returns: object

search_snippetsB

Search for text snippets from paper full texts, abstracts, and titles matching a query, with optional filters.

Inputs: query (required), venue, paper_ids, insertion_ids, +3 more. Returns: object

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.6/5.0

    Scored across 14 tools

    Disambiguation5/5

    Each tool targets a distinct operation: search vs. retrieval vs. authors vs. references/citations. Even the search variants (search_papers, search_papers_bulk, match_paper_title, autocomplete_paper) are clearly differentiated by their descriptions—relevance ranking, bulk output, exact title match, and title completion.

    Naming Consistency5/5

    All tools follow a consistent verb_noun pattern in snake_case (get_, search_, match_, autocomplete_). Plural/singular usage is logical (get_paper vs get_papers_batch) and the bulk suffix is uniformly applied.

    Tool Count5/5

    14 tools is well within the ideal range for a scholarly data API. Each tool covers a meaningful aspect of paper and author retrieval, with bulk and single-item variants earning their place.

    Completeness5/5

    The tool surface covers the full read-only lifecycle: paper search, paper details, references, citations, author search, author details, author papers, and bulk operations. No obvious dead ends or missing operations for the stated domain.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers