← All integrations

Semantic Scholar MCP server

21 operations0 webhooks

Academic search API for papers, authors, citations, references, paper recommendations, text snippets, and dataset releases.

Use Semantic Scholar in Claude, ChatGPT, Cursor or another MCP client

Connect Semantic Scholar once in Corsair, then add one MCP address to your agent.

Connect Semantic Scholar
Setup steps for Claude, ChatGPT, Cursor and Claude Code

Building your own app on the Corsair SDK? Get API keys

Try Semantic Scholar with your agent

Connect Semantic Scholar, then paste this into Claude, ChatGPT or Cursor. For ideas from other apps, see the use cases.

Using Corsair, show me what you can do in Semantic Scholar on my account, then run one read-only example and show me the result.

Runs once, when you ask

Semantic Scholar tools and triggers

Tools are what your agent can do in Semantic Scholar through Corsair's MCP server. Triggers are the Semantic Scholar events a routine can start from.

Papers

  • AutocompleteRead-only

    Suggest paper query completions for a partial query

    papers.autocomplete

  • Batch GetRead-only

    Retrieve details for up to 500 papers in one request

    papers.batchGet

  • GetRead-only

    Retrieve details about a paper by Semantic Scholar-supported ID

    papers.get

  • List AuthorsRead-only

    List authors for a paper with offset pagination

    papers.listAuthors

  • List CitationsRead-only

    List papers that cite a paper with offset pagination

    papers.listCitations

  • List ReferencesRead-only

    List references cited by a paper with offset pagination

    papers.listReferences

  • Match TitleRead-only

    Find the closest paper title match for a query

    papers.matchTitle

  • Relevance SearchRead-only

    Deprecated alias for paper relevance search; use papers.search for new code

    papers.relevanceSearch

  • SearchRead-only

    Search papers by relevance with optional publication filters

    papers.search

  • Search BulkRead-only

    Bulk search papers with token pagination and optional sorting

    papers.searchBulk

Authors

  • Batch GetRead-only

    Retrieve details for up to 1000 authors in one request

    authors.batchGet

  • GetRead-only

    Retrieve details about an author by Semantic Scholar author ID

    authors.get

Connect Semantic Scholar to Claude, ChatGPT or Cursor

  1. 1

    Connect Semantic Scholar in Corsair

    Add your Semantic Scholar API key once in Corsair. Corsair stores the credential encrypted and makes the Semantic Scholar API calls for your agent, so it never goes into a prompt or a config file. Connect Semantic Scholar

    If your link lets the agent add apps, you can skip this: it gives you a sign-in link the first time it needs Semantic Scholar. On a ChatGPT personal plan, connect Semantic Scholar here first.

  2. 2

    Add Corsair's MCP server to your agent

    Every client uses the same address:

    https://mcp.corsair.dev/mcp
    Open Customize → Connectors → Add custom connector, paste the address, then select Connect.

    Codex, Gemini CLI, VS Code, Zed and other clients with OAuth sign-in work the same way. Clients without it, such as GitHub Copilot's coding agent, use a link's own address and an API key. Setup for every client

  3. 3

    Sign in and choose what needs your approval

    Your client opens Corsair to sign in. Pick a link: the apps your agent can use and a mode that decides what it may do without asking. Every Semantic Scholar operation only reads data, so it runs right away in every mode.

FAQ

Install corsair and @corsair-dev/semanticscholar, add the Semantic Scholar plugin, and connect with an API key. Then call methods like corsair.semanticscholar.api.authors.batchGet() from your app. Corsair syncs data per tenant.

Yes. Semantic Scholar requires an API key from your Semantic Scholar account or developer dashboard. Create credentials with access that matches what you automate, then paste them into Corsair or connect through managed auth in Hub.

Yes. One Corsair client can hit Semantic Scholar, GitHub, Notion, Stripe, and the rest. Trigger Semantic Scholar from a webhook, push updates to Slack, or chain actions across plugins. Same tenant context across integrations, plain TypeScript.

Teams use Corsair for academic search api for papers, authors, citations, references, paper recommendations, text snippets, and dataset releases. Common builds include sync jobs, admin tooling, and agents that call Semantic Scholar APIs from your backend. Local DB entities let you query synced Semantic Scholar records without hitting the API on every read.

The SDK is open source. Self-host and you pay Corsair nothing for the integration layer. Hub bills for hosted auth and execution, not per Semantic Scholar API call. Hub has a generous free tier. For hobby projects you can probably run the whole thing on free. Paid plans start to matter with more tenants or heavier traffic.

We maintain @corsair-dev/semanticscholar in the open repo. When Semantic Scholar ships API changes, upgrade the package. Your call sites stay typed. You should not need to rewrite the integration layer each time.

No. Corsair does not read your Semantic Scholar data or hold individual access credentials. Credentials stay in your database. API calls run on your instance. We do not store Semantic Scholar data on your behalf.

Yes. Add https://mcp.corsair.dev/mcp as a custom connector or MCP server in Claude, ChatGPT, Cursor, VS Code, Claude Code, Codex or any client that supports remote MCP servers with OAuth sign-in, then sign in to Corsair. On ChatGPT personal plans, custom servers currently get read tools only.

Yes. Put Semantic Scholar on a link in Strict mode and every write waits for your approval, while destructive actions are refused. Every Semantic Scholar operation only reads data, so there are no changes to approve today. You can change a link's mode at hub.corsair.dev/me.