An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Stanford Semantic Scholar to ChatGPT and Claude

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Access the world's largest academic knowledge graph through your agent.

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

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 16 capabilities

We ship only the actions that matter.

Capability set01 / 04

01-04

4 capabilities in this set.

Part of 16 available through Semantic Scholar.

  1. 01

    Batch get authors

    Retrieves multiple author profiles at once. Use this to compare researcher metrics like h-index and citation counts in a single request.

  2. 02

    Get paper

    Fetches full metadata for a specific paper. You can provide a DOI, ArXiv ID, PubMed ID, or Semantic Scholar ID to get the abstract, authors, and open access links.

  3. 03

    Search authors

    Searches the academic graph for specific researchers. It returns their affiliations, paper counts, and citation impact.

  4. 04

    Get recommendations

    Provides AI-driven paper suggestions based on a single seed paper. It uses citation patterns and content similarity to find what you should read next.

Capability set02 / 04

05-08

4 capabilities in this set.

Part of 16 available through Semantic Scholar.

  1. 05

    Search by field

    Filters paper searches by specific academic disciplines. You can narrow results to fields like Biology, Physics, or Computer Science.

  2. 06

    Batch get papers

    Retrieves a collection of papers using their IDs. This is useful for building reading lists or analyzing a specific set of works.

  3. 07

    Bulk search papers

    Performs large scale searches using pagination tokens. Use this for systematic literature reviews that require hundreds of results.

  4. 08

    Get author

    Returns a detailed profile for a single researcher. It includes their h-index, total citations, and external IDs like ORCID.

Capability set03 / 04

09-12

4 capabilities in this set.

Part of 16 available through Semantic Scholar.

  1. 09

    Get author papers

    Lists all publications for a specific researcher. It provides titles, years, and venue information for their entire body of work.

  2. 10

    Get multi recommendations

    Generates paper suggestions using both positive and negative signals. This allows you to refine recommendations by telling the agent what to include or avoid.

  3. 11

    Get paper authors

    Identifies the researchers behind a specific paper. It includes their individual metrics to help you find leaders in a field.

  4. 12

    Get paper citations

    Finds all papers that have cited a specific work. This helps you track how a particular research idea has evolved over time.

Capability set04 / 04

13-16

4 capabilities in this set.

Part of 16 available through Semantic Scholar.

  1. 13

    Get paper references

    Retrieves the list of papers cited by a specific work. Use this to find the foundational research that a paper is built upon.

  2. 14

    Match paper title

    Uses fuzzy matching to find a paper when you only have a partial or slightly incorrect title. It returns the best match from the database.

  3. 15

    Search by venue

    Filters searches to specific journals or conferences. You can target top-tier venues like Nature, Science, or NeurIPS.

  4. 16

    Search papers

    Searches the full database of 200M+ papers. You can filter by keyword, year range, field, or open access status.

Real work

What teams actually run

01

Literature Reviews

Your agent can perform bulk searches and gather all necessary metadata for a specific topic.

02

Tracking Research Trends

Use venue filtering to see what is being published in top conferences like NeurIPS or ICML.

03

Author Verification

Check an author's total impact and publication history before citing them.

04

Finding Related Work

Use seed papers to trigger AI-powered recommendations for similar research.

Automate a task

Put Semantic Scholar to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Semantic Scholar works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put Semantic Scholar to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

954ms average. Fast in production.

Semantic Scholar is checked daily against the live service.

Daily averagePeak 1494ms
Oct 6Today
Fastest day
798ms
Slowest day
1494ms
14-day trend
Improving-7%

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

Guided setup for Claude? Set up Semantic Scholar in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Semantic Scholar owners hand off.

This MCP is built for anyone working within the academic or scientific research ecosystem. It turns your AI client into a research assistant that can navigate complex citation networks.

  • 01

    Researchers

    Conduct literature reviews and map out citation chains for new projects.

  • 02

    PhD Students

    Navigate the academic graph to find foundational papers and position their own work.

  • 03

    Data Scientists

    Build bibliometric analyses and publication datasets for research trends.

  • 04

    R&D Teams

    Monitor new publications in specific domains to stay ahead of industry trends.

FAQ

Questions Semantic Scholar owners ask.

  • 01

    Do I need an API key for Semantic Scholar?

    No, this MCP uses the public Semantic Scholar API, so no personal API key is required to start searching.

  • 02

    Which AI clients can use this MCP?

    You can use this with any MCP-compatible client, including Claude, Cursor, and Windsurf.

  • 03

    Can I search for papers using a DOI?

    Yes, the get_paper capability accepts DOIs, ArXiv IDs, PubMed IDs, and Semantic Scholar IDs.

  • 04

    How many papers are in the database?

    The Semantic Scholar Academic Graph contains over 200 million academic papers.

  • 05

    Can I filter results by a specific field of study?

    Yes, you can use the search_by_field capability to narrow results to fields like Physics, Medicine, or Computer Science.

  • 06

    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.

  • 07

    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.

  • 08

    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

Connect Semantic Scholar to Claude, Cursor, ChatGPT & more