← All integrations

TextCortex MCP server

7 operations0 webhooks

Text generation with TextCortex - list the models, read the credit balance and enabled capabilities, run chat completions and single responses, generate images, and search the web.

Try TextCortex with your agent

Connect TextCortex, 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 TextCortex on my account, then run one read-only example and show me the result.

Runs once, when you ask

TextCortex tools and triggers

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

Balance

  • GetRead-only

    Read the remaining API credits, the funding source and the wallet amount

    balance.get

Capabilities

  • GetRead-only

    Read the features enabled for the key, such as image generation

    capabilities.get

Chat

  • CompletionsDestructive

    Generate a chat completion from a conversation, which spends credits on every call

    chat.completions

Images

  • CreateDestructive

    Generate an image from a prompt, returning its URL, and spend credits per image

    images.create

Models

  • ListRead-only

    List the chat models available to the key, with their IDs and owners

    models.list

Responses

  • CreateDestructive

    Generate one response from a prompt and optional instructions, which spends credits

    responses.create

Web

  • SearchRead-only

    Search the web and return matching sources with snippets; each search spends credits

    web.search

Connect TextCortex to Claude, ChatGPT or Cursor

  1. 1

    Connect TextCortex in Corsair

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

    If your link lets the agent add apps, you can skip this: it gives you a sign-in link the first time it needs TextCortex. On a ChatGPT personal plan, connect TextCortex 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. In the default Cautious mode, TextCortex's read and write operations run right away and its 3 destructive operations wait for your approval. Strict mode asks before every write and refuses destructive operations, and Read mode allows reads only.

FAQ

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

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

Teams use Corsair for text generation with TextCortex - list the models, read the credit balance and enabled capabilities, run chat completions and single responses, generate images, and search the web. Common builds include sync jobs, admin tooling, and agents that call TextCortex 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 TextCortex 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/textcortex in the open repo. When TextCortex 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 TextCortex data or hold individual access credentials. Credentials stay in your database. API calls run on your instance. We do not store TextCortex 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 TextCortex on a link in Strict mode and every write waits for your approval, while destructive actions are refused. The default Cautious mode asks only before the 3 destructive TextCortex operations. You can change a link's mode at hub.corsair.dev/me.