← All integrations

Canny MCP server

13 operations4 webhooks

Customer feedback platform. Manage boards, feedback posts, comments, and votes.

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

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

Connect Canny
Setup steps for Claude, ChatGPT, Cursor and Claude Code

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

Try Canny with your agent

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

Runs once, when you ask

Canny tools and triggers

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

Posts

  • Change StatusWrite

    Change an existing Canny post's status

    posts.changeStatus

  • CreateWrite

    Create a new post in Canny

    posts.create

  • DeleteDestructive

    Delete a post in Canny [DESTRUCTIVE · IRREVERSIBLE]

    posts.delete

  • ListRead-only

    List posts in Canny with optional filtering and pagination

    posts.list

  • RetrieveRead-only

    Retrieve details of an existing Canny post by ID

    posts.retrieve

Comments

  • CreateWrite

    Create a new comment on a Canny post

    comments.create

  • DeleteDestructive

    Delete a comment in Canny [DESTRUCTIVE · IRREVERSIBLE]

    comments.delete

  • ListRead-only

    List comments in Canny with optional filtering and pagination

    comments.list

Votes

  • CreateWrite

    Create a vote for a Canny post on behalf of a user

    votes.create

  • DeleteDestructive

    Delete a vote on a Canny post [DESTRUCTIVE · IRREVERSIBLE]

    votes.delete

  • ListRead-only

    List votes in Canny with optional filtering and pagination

    votes.list

Boards

  • ListRead-only

    List all boards for your company in Canny

    boards.list

Connect Canny to Claude, ChatGPT or Cursor

  1. 1

    Connect Canny in Corsair

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

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

Canny works with

IntercomNotify Intercom contacts when their Canny votes ship.LinearTurn high-impact feature votes into Linear issues and projects.SlackPost Canny status changes and top votes to #product-feedback.

FAQ

Install corsair and @corsair-dev/canny, add the Canny plugin, and connect with an API key. Then call methods like corsair.canny.api.boards.list() from your app. Corsair verifies webhooks, and syncs data per tenant.

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

Teams use Corsair for customer feedback platform. manage boards, feedback posts, comments, and votes. Common builds include sync jobs, admin tooling, and agents that call Canny APIs from your backend. Webhook handlers react to Canny events and fan out to Slack, email, or other plugins in the same tenant. Local DB entities let you query synced Canny 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 Canny 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/canny in the open repo. When Canny 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 Canny data or hold individual access credentials. Credentials stay in your database. API calls run on your instance. We do not store Canny 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 Canny 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 Canny operations. You can change a link's mode at hub.corsair.dev/me.