Canny integration for AI agents.
Canny integration for AI agents with secure authentication and server-side credential injection. Open Connector runs the OAuth, seals the token in an encrypted vault, and serves Canny tools to your agent over MCP or a typed API — credentials injected server-side, every call audited, nothing leaving your infrastructure. Open source (AGPL-3.0) and self-hostable.
Real Canny actions, managed and audited.
Your user connects Canny once; your agent can then manage Canny product feedback boards, posts, comments, users, votes, tags, and categories — scoped to the OAuth permissions you grant and the tool allowlist you configure. Every action is least-privilege and written to a tamper-evident audit trail.
- 1
Your user grants Canny access once (OAuth) — the token lands in the vault.
- 2
Your agent calls a tool over MCP or the typed API; Open Connector injects the credential server-side.
- 3
Every routed call appends a hash-chained audit record — nothing leaves your infra.
Supported Canny tools.
18 tools are generated from the published Canny catalog. Descriptions are plain text; each action remains subject to its configured authentication and tool allowlist.
Showing 18 tools. All published catalog entries are included in this page's server-rendered HTML.
- Change post status
- Changes a Canny post status and optionally notifies voters or adds a status comment.
- Posts
- Create category
- Creates a new Canny category for a board.
- Categories
- Create comment
- Creates a comment on a Canny post.
- Comments
- Create or update user
- Creates or updates a Canny user and optionally associates companies and custom fields.
- Users
- Create post
- Creates a new Canny post.
- Posts
- Create tag
- Creates a new Canny tag for a board.
- Tags
- Create vote
- Creates a vote for a Canny post.
- Votes
- Delete comment
- Deletes a Canny comment.
- Comments
- Delete post
- Deletes an existing Canny post.
- Posts
- Delete vote
- Deletes a vote from a Canny post.
- Votes
- List boards
- Returns all Canny boards associated with the company.
- Boards
- List categories
- Lists Canny categories, optionally scoped to a board.
- Categories
- List posts
- Lists Canny posts with optional board, status, search, sort, and pagination filters.
- Posts
- List tags
- Lists Canny tags, optionally scoped to a board.
- Tags
- Retrieve board
- Retrieves an existing board by ID.
- Boards
- Retrieve post
- Retrieves a Canny post by ID, or by URL name with board ID.
- Posts
- Retrieve user
- Retrieves a Canny user by ID.
- Users
- Update post
- Updates an existing Canny post.
- Posts
Canny integration, answered
- How do AI agents use Canny through Open Connector?
- Your user connects Canny once with one of its cataloged authentication methods. Open Connector stores the credential in an encrypted vault and exposes Canny tools to your agent over MCP or a typed API, with credentials injected server-side on each call.
- Is this a Canny MCP server?
- Yes. Open Connector can serve Canny as a named MCP server with a scoped allowlist and a per-user connection URL, so any MCP client can call Canny actions with credentials injected server-side.
- Where do Canny credentials live?
- In your own infrastructure. Open Connector keeps credentials in its own vault and injects them at call time, so they never leave your environment.
Give your agents Canny — keep the keys.
Open source, self-hostable, with Canny credentials that never leave your infrastructure. Run it from source today.