Download PDFMarkdown Version
ClaudeChatGPTPerplexityGeminiMicrosoft CopilotRaycastMeta AIGrokZ.aiQwenKimi
DeepSeekMistralCursorVS CodeWindsurfJetBrainsClineLovableVercel AI SDKLangChain

Use Semantic Scholar with your AI.

Connect your account once and let the AI you already use work with it, without building another integration. Discover academic papers with AI-powered search that understands research context, finds citations, and recommends related work.

Included with plan

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Complete set · 16 capabilities

The complete Semantic Scholar capability set.

These are the exact actions your AI can choose when you ask it to work with Semantic Scholar.

Capability set01 / 04

01-04

4 capabilities in this set.

Part of 16 available through Semantic Scholar.

  1. 01

    Batch get authors

    Returns names, affiliations, paper counts, citation counts, and h-indices. Useful for comparing researchers or building collaboration network analyses. Retrieve multiple author profiles in a single request

  2. 02

    Get paper

    Accepts multiple ID formats: Semantic Scholar ID (e.g. "649def34f8be52c8b66281af98ae884c09aef38b"), DOI (e.g. "10.1038/s41586-021-03819-2"), ArXiv ID (e.g. "arXiv:2106.09685"), PubMed ID (e.g. "PMID:34845388"), or ACL ID (e.g. "ACL:W12-3903"). Returns title, abstract, authors, venue, year, citation counts, open access PDF URL, and publication metadata. Get full paper details by ID, DOI, ArXiv ID, or PubMed ID

  3. 03

    Search authors

    Returns author profiles with affiliations, paper counts, citation counts, and h-index. Use this to find researchers in a specific field, discover top contributors, or find collaborators. Search authors by name across the academic graph

  4. 04

    Get recommendations

    The algorithm analyzes citation patterns, co-citation networks, and content similarity to find the most relevant papers you should read next. This is the AI-native way to discover related literature. Get AI-powered paper recommendations from a seed paper

Capability set02 / 04

05-08

4 capabilities in this set.

Part of 16 available through Semantic Scholar.

  1. 05

    Search by field

    Supported fields: Computer Science, Medicine, Biology, Chemistry, Physics, Mathematics, Engineering, Environmental Science, Economics, Business, Political Science, Sociology, Psychology, Art, History, Geography, Philosophy, Materials Science, Geology, Linguistics, Education, Agricultural and Food Sciences, Law. Search papers filtered by field of study

  2. 06

    Batch get papers

    Accepts S2 IDs, DOIs, ArXiv IDs, or PubMed IDs. Useful for comparing papers, building reading lists, or analyzing a set of related works. Retrieve multiple papers in a single request

  3. 07

    Bulk search papers

    Each call returns a batch of results plus a continuation token. Pass the token in subsequent calls to get the next batch. Ideal for systematic literature reviews and meta-analyses. Bulk search for large result sets with token pagination

  4. 08

    Get author

    Returns name, affiliations, homepage, external IDs (DBLP, ORCID), total paper count, citation count, and h-index. The definitive capability for understanding a researcher's academic impact. Get author profile with h-index, citations, and metrics

Capability set03 / 04

09-12

4 capabilities in this set.

Part of 16 available through Semantic Scholar.

  1. 09

    Get author papers

    Returns papers with titles, years, venues, citation counts, open access status, and fields of study. Essential for reviewing a researcher's body of work or finding specific publications by a known author. Get all papers by a specific author

  2. 10

    Get multi recommendations

    The algorithm finds papers similar to the positive set but dissimilar to the negative set. Ideal for focused literature discovery. Get recommendations from multiple seed papers with positive/negative signals

  3. 11

    Get paper authors

    Useful for identifying research leaders and collaboration networks. Get authors of a specific paper with h-index and metrics

  4. 12

    Get paper citations

    This is essential for understanding a paper's impact, finding follow-up work, and tracing how an idea has evolved. Returns citing paper metadata including titles, venues, years, and citation counts. Get papers that cite a given paper

Capability set04 / 04

13-16

4 capabilities in this set.

Part of 16 available through Semantic Scholar.

  1. 13

    Get paper references

    Essential for literature reviews, understanding the intellectual lineage of a work, and finding foundational papers in a research area. Get papers referenced by a given paper

  2. 14

    Match paper title

    Uses fuzzy matching to handle slight variations. Returns the best matching paper with a match score. Ideal when you have a paper title from a reference list or bibliography and need to find its full metadata. Find an exact paper match from a title string

  3. 15

    Search by venue

    Use venue names like "Nature", "Science", "NeurIPS", "ICML", "CVPR", "ACL", "EMNLP", "The Lancet", "JAMA", "Cell", "Physical Review Letters". Essential for tracking publications in specific top-tier venues. Search papers filtered by conference or journal

  4. 16

    Search papers

    Returns titles, venues, years, citation counts, open access status, fields of study, and authors. Supports filtering by year range (e.g. "2020-2024"), fields of study (e.g. "Computer Science"), venue (e.g. "Nature"), and open access availability. Search across 200M+ academic papers by keyword

Observed, not estimated

1012ms average. Fast in production.

Semantic Scholar is checked daily against the live service.

Daily averagePeak 1263ms
Aug 21Today
Fastest day
851ms
Slowest day
1263ms
14-day trend
Improving-21%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 16 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Semantic Scholar, so you can see the experience inside your AI.

It does not authenticate your account with Semantic Scholar. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Semantic Scholar Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_AZJpPbxBFEPF3qqoPfdyST9yhfXQRp6VrfLZlw40/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Semantic Scholar capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "stanford-semantic-scholar-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_AZJpPbxBFEPF3qqoPfdyST9yhfXQRp6VrfLZlw40/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

FAQ

Questions Semantic Scholar owners ask.

  • 01

    Do I need an API key?

    No. The Semantic Scholar API is fully public. An optional free API key increases rate limits from 1 to 10 requests per second.

  • 02

    What paper ID formats are supported?

    Semantic Scholar accepts multiple ID formats: its own S2 Paper ID, DOI (e.g. "10.1038/..."), ArXiv ID (e.g. "arXiv:2106.09685"), PubMed ID (e.g. "PMID:34845388"), and ACL Anthology ID. This makes it easy to look up any paper regardless of where you found the reference.

  • 03

    How do the AI recommendations work?

    The recommendation engine uses machine learning to analyze citation patterns, co-citation networks, and content similarity. You can provide one seed paper for basic recommendations, or multiple positive and negative seed papers for advanced filtering. This is the most sophisticated way to discover related literature.

Explore

More in Education

Suggestions