What you can do with Semantic Scholar

Built for

Academic Researchers, PhD Students, R&D Teams, Literature Review Leads

Example workflows

Search the paper corpus

Keyword discovery across the Semantic Scholar paper index.

Try this

Search Semantic Scholar for retrieval-augmented generation papers from the last three years and summarize the top matches with citation counts.

Citation network on one paper

Incoming and outgoing citation edges for impact analysis.

Try this

Find Attention Is All You Need in Semantic Scholar, then list its citations and references and highlight the five most influential citing papers.

Expand a reading list

Recommendation and similarity tools for review expansion.

Try this

Given three core papers on AI agents, recommend similar Semantic Scholar papers I should read next and explain why each fits.

Author and snippet research

Author profiles plus snippet search for targeted evidence gathering.

Try this

Search Semantic Scholar for Yoshua Bengio, pull his recent papers, and find snippet passages about scaling laws across his work.

Context to know first

What is Semantic Scholar MCP?

It lets AI agents search Semantic Scholar's catalog of 214M+ papers, open paper and author profiles, walk citations and references, and surface recommended reads after you add the server in MCPBundles.

Who is Semantic Scholar MCP for?

Researchers and review leads who need paper discovery, citation context, author lookup, and reading-list expansion without leaving their AI chat.

Can an agent map citations from chat?

Yes. Open a paper, then list papers that cite it or papers it references to trace influence, find seminal work, or build a structured review outline.

Related editorial

Semantic Scholar Research Workflows with AI

How AI agents can search Semantic Scholar's paper corpus, explore citations and references, look up authors, and expand reading lists from chat.

Read article

AI Skill
SKILL.md

Domain knowledge for Semantic Scholar — workflow patterns, data models, and gotchas for your AI agent.

Semantic Scholar

Semantic Scholar provides Academic Graph and Recommendations APIs. Search 214M+ papers, explore citations, discover authors, get recommendations. Configured credentials get a dedicated rate-limit pool.

Data Model

  • Papers — keyword search, id lookup, fuzzy matching, batch hydration, similarity neighborhoods, and personalized recommendations.
  • Authors — search, profile pages, authorship expansion, and batched author metadata.
  • Citations & references — outgoing and incoming graph edges per paper id.
  • Snippets — full-text style passage search across the corpus.

Gotchas

  • Rate limits: 120/min hard cap. Without configured credentials, requests share a global pool. With configured credentials, you get a dedicated 1 RPS baseline.
  • HTTP 429: Back off and retry; configured credentials raise the per-second cap. Use paper/author id lookups (e.g. get paper by DOI) instead of heavy search when the shared pool is saturated.

Tools in this Server (14)

Batch Authors

Fetch Semantic Scholar details for multiple authors in a single request (up to 1000 IDs). Returns name, affiliations, paper count, citation count, and...

Batch Papers

Fetch Semantic Scholar details for multiple papers in a single request (up to 500 IDs). Returns title, abstract, authors, citation count, venue, and m...

Get Author

Fetch detailed Semantic Scholar author profile including name, affiliations, homepage, paper count, citation count, h-index, and external IDs (DBLP, e...

Get Author Papers

Get a Semantic Scholar author's papers with title, year, venue, citation count, and co-author information. Paginated for authors with many publication...

Get Citations

Get Semantic Scholar papers that cite a given paper (incoming citations). Returns citing papers with context snippets, citation intents, and whether t...

Get Paper

Fetch full Semantic Scholar paper metadata including abstract, authors, citation/reference counts, fields of study, and publication details. Accepts p...

Get Paper Authors

Get the authors of a Semantic Scholar paper with their affiliations, publication count, citation count, and h-index.

Get References

Get Semantic Scholar papers referenced by a given paper (bibliography/outgoing references). Returns referenced papers with context snippets, citation ...

Match Paper

Find a single Semantic Scholar paper by exact or close title match. Returns the best-matching paper with a match score. Use this when you know the pap...

Recommend Papers

Get paper recommendations based on lists of positive (and optionally negative) example papers (Semantic Scholar Recommendations API). Provide papers y...

Search Authors

Search Semantic Scholar for authors by name. Returns authors with their affiliations, paper count, citation count, and h-index.

Search Papers

Search Semantic Scholar papers by relevance (Academic Graph API). Returns papers with title, abstract, TLDR summary, authors, venue, citation count, a...

Search Snippets

Search for text snippets (~500 words) across academic papers that match a query. Returns ranked text excerpts from titles, abstracts, and body text wi...

Similar Papers

Get paper recommendations similar to a single input paper (Semantic Scholar Recommendations API). Choose from 'recent' papers across all fields or 'al...

Frequently Asked Questions

What is Semantic Scholar MCP?

It lets AI agents search Semantic Scholar's catalog of 214M+ papers, open paper and author profiles, walk citations and references, and surface recommended reads after you add the server in MCPBundles.

Who is Semantic Scholar MCP for?

Researchers and review leads who need paper discovery, citation context, author lookup, and reading-list expansion without leaving their AI chat.

Can an agent map citations from chat?

Yes. Open a paper, then list papers that cite it or papers it references to trace influence, find seminal work, or build a structured review outline.

How do I connect?

Add the server in MCPBundles and start searching. Optional free access from Semantic Scholar improves rate limits for sustained literature review sessions.

How do I connect Semantic Scholar to my AI agent?

Add the MCPBundles server URL to your MCP client configuration (Claude Desktop, Cursor, VS Code, etc.). The URL format is: https://mcp.mcpbundles.com/bundle/semantic-scholar. Authentication is handled automatically.

How many tools does Semantic Scholar provide?

Semantic Scholar provides 14 tools that can be called by AI agents, along with a SKILL.md that gives your AI agent domain knowledge about when and how to use them.

What authentication does Semantic Scholar require?

Semantic Scholar uses open data APIs — no authentication required.

Setup Instructions

Connect Semantic Scholar to any MCP client in minutes

MCP URL
https://mcp.mcpbundles.com/bundle/semantic-scholar

One-click install:

The link prefills the Add custom connector dialog — you still review the values and click Add, then Connect to complete OAuth.

Or add manually

  1. Open claude.ai → Settings → Connectors.
  2. Click the + button and choose Add custom connector.
  3. Set Name to Semantic Scholar and paste the MCP URL into Remote MCP server URL.
  4. Click Add. Semantic Scholar will appear under Not connected — select it and click Connect to complete OAuth.
Name: Semantic Scholar
Remote MCP server URL: https://mcp.mcpbundles.com/bundle/semantic-scholar
Authentication: OAuth

Custom connectors at claude.ai require a paid Claude plan (Pro, Max, Team, or Enterprise).

Try Semantic Scholar now

No API key or third-party login required. Chat with AI and run tools instantly.

Semantic Scholar MCP Server