Semanticscholar

io.github.SMABoundlessPublished by GitHub account SMABoundlessv1.0.0Updated Oct 24, 2026

Search 200M+ papers, authors, citations, and recommendations via Semantic Scholar

VerifiedSTDIODesktop onlyWeb Search & ScrapingKnowledge & Memory

Overview

AI-generated overview

Searches Semantic Scholar's 200M+ paper graph, letting an assistant find papers, authors, citations and recommendations.

What you can do
Search, match, autocomplete and batch-retrieve papers by keyword, title or ID (DOI, ArXiv, PMID and others). Explore citation networks: forward citations, reference lists and per-paper author details. Look up author profiles, search authors by name and list an author's papers. Get ML-powered recommendations from a paper or from positive and negative example papers. Search inside paper bodies for specific text passages.
When to use it
Useful for literature reviews, citation tracing, finding related work, checking an author's record, or locating a passage inside a paper. Fits research and academic writing workflows where an assistant needs structured scholarly data.
Requirements
Runs locally as an npm package via npx, so Node.js is needed. An optional Semantic Scholar API key is supplied through the SEMANTICSCHOLAR_API_KEY environment variable; without it, requests are heavily rate-limited. Network access to the Semantic Scholar API is required.
Before you install
The API key is a secret passed in the environment; keep it out of shared configs. Without a key, rate limits may make the server unreliable. All tools read public scholarly data; no writing, sending or deleting is described.

Installation

In SourceWeft

  1. Open Semanticscholar in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

Semantic Scholar MCP Server

An MCP (Model Context Protocol) server for the Semantic Scholar Academic Graph API — 200M+ papers with citation networks, author profiles, and full-text snippet search.

Built with the MCP TypeScript SDK and Zod.

Tools (16 total)

Papers (9 tools)

ToolDescription
paper_searchSearch papers by keyword with filtering (year, venue, field, open access, citations, type)
paper_search_bulkBulk search with cursor pagination for large result sets (up to 10M)
paper_matchFind the single best match for a known paper title
paper_autocompleteAutocomplete partial paper titles (up to 10 suggestions)
paper_getGet full details for a paper by ID (S2 ID, DOI, ArXiv, PMID, etc.)
paper_batchRetrieve up to 500 papers in a single request
paper_citationsGet papers that cite a given paper (forward citations)
paper_referencesGet a paper's reference list (bibliography)
paper_authorsGet author details for a specific paper

Authors (4 tools)

ToolDescription
author_getGet full author profile (h-index, affiliations, stats)
author_batchRetrieve up to 1000 author profiles in one request
author_searchSearch for authors by name
author_papersGet all papers by a specific author

Recommendations (2 tools)

ToolDescription
recommendations_for_paperGet ML-powered paper recommendations for a given paper
recommendations_from_listsGet recommendations from positive/negative example papers

Snippets (1 tool)

ToolDescription
snippet_searchSearch within paper bodies for specific text passages

Setup

1. Get an API key (optional but recommended)

Get a free key at semanticscholar.org/product/api. Without a key, requests are heavily rate-limited.

2. Install and build

bash
cd semanticscholar-mcp-servernpm installnpm run build

3. Add to Claude Desktop

Add this to your claude_desktop_config.json:

json
{  "mcpServers": {    "semantic-scholar": {      "command": "node",      "args": ["/path/to/semanticscholar-mcp-server/dist/index.js"],      "env": {        "SEMANTICSCHOLAR_API_KEY": "your-api-key"      }    }  }}

Or if using Claude Code CLI:

bash
claude mcp add semantic-scholar \  node \  /path/to/semanticscholar-mcp-server/dist/index.js \  -e SEMANTICSCHOLAR_API_KEY=your-api-key

Features

  • Multiple ID formats: Accepts S2 Paper IDs, DOIs, ArXiv IDs, PMIDs, PMCIDs, CorpusIds
  • Markdown or JSON output: Every tool supports response_format: "json" for structured data
  • Custom field selection: Override default fields with the fields parameter
  • Built-in rate limiting: Token bucket limiter prevents API throttling
  • Batch operations: Retrieve up to 500 papers or 1000 authors in a single call

Usage examples

  • "Search Semantic Scholar for papers on transformer architectures from 2023"
  • "Get recommendations for papers similar to this one"
  • "Find the citation network for DOI 10.1038/nature14539"
  • "Search for text snippets mentioning 'chain of thought prompting'"
  • "Look up author profile for researcher 1741101"

License

MIT

Source: README.md at commit c9e9779

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v1.0.0LatestSep 16, 2026

Score

40% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.