← All integrations

TypeSafe MCP server

2 operations0 webhooks

Ask Jev, TypeSafe's System One model, typed questions about text, JSON or images and get calibrated probabilities back for code to act on.

Use TypeSafe in Claude, ChatGPT, Cursor or another MCP client

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

Connect TypeSafe

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

Connect TypeSafe to Claude, ChatGPT or Cursor

  1. 1

    Connect TypeSafe in Corsair

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

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

  2. 2

    Add Corsair's MCP server to your agent

    Every client uses the same address:

    https://mcp.corsair.dev/mcp

    Claude

    Open Customize → Connectors → Add custom connector, paste the address, then select Connect.

    ChatGPT

    Add a custom MCP server with the address and choose OAuth. Personal plans get read tools only.

    Cursor

    Add to CursorOr add this to ~/.cursor/mcp.json. Cursor opens Corsair to sign in the first time it connects.
    {
  "mcpServers": {
    "corsair": { "url": "https://mcp.corsair.dev/mcp" }
  }
}

    Claude Code

    Run this, then run /mcp in Claude Code to sign in.claude mcp add --transport http corsair https://mcp.corsair.dev/mcp

    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 TypeSafe operation only reads data, so it runs right away in every mode.

TypeSafe operations available through MCP

  • ListRead-only

    List the TypeSafe model names and aliases this key can use, such as jev-latest

FAQ

Install corsair and @corsair-dev/typesafe, add the TypeSafe plugin, and connect with an API key. Then call methods like corsair.typesafe.api.models.list() from your app. Corsair keeps each tenant isolated.

Yes. TypeSafe requires an API key from your TypeSafe 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 TypeSafe, GitHub, Notion, Stripe, and the rest. Trigger TypeSafe from a webhook, push updates to Slack, or chain actions across plugins. Same tenant context across integrations, plain TypeScript.

Teams use Corsair for ask jev, typesafe's system one model, typed questions about text, json or images and get calibrated probabilities back for code to act on. Common builds include sync jobs, admin tooling, and agents that call TypeSafe APIs from your backend.

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 TypeSafe 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/typesafe in the open repo. When TypeSafe 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 TypeSafe data or hold individual access credentials. Credentials stay in your database. API calls run on your instance. We do not store TypeSafe 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 TypeSafe on a link in Strict mode and every write waits for your approval, while destructive actions are refused. Every TypeSafe operation only reads data, so there are no changes to approve today. You can change a link's mode at hub.corsair.dev/me.