Canny MCP integration for AI agents.
Connect AI agents to Canny through 11 structured actions, including list boards, create comment, and create or update user. Review authentication, inputs, wo…
- ACTION CONTRACTS
- 11
- AUTHENTICATION
- API key
- SOURCE STATUS
- Provider-backed
CATALOG SOURCE REVIEWED AUGUST 23, 2026 / ACTION NAMES AND SCHEMAS DERIVED FROM WORKING MACHINES PROVIDER SOURCE
CAPABILITY PROFILE
What the Canny integration exposes
The Canny Agent App exposes 11 provider-backed actions for productivity and data work. Its current contract lets an authorized agent list all canny boards available to the authenticated workspace, create a new canny comment on a post or as a reply to a comment, and create a new canny user or update an existing one by id, userid, or email. These operations are called through Working Machines as typed capabilities rather than through browser navigation or copied UI steps.
A connection uses API key. Before execution, the agent can inspect the selected action, its required fields, declared scopes, and expected output contract. Provider credentials remain inside the Working Machines runtime; the calling agent receives the capability and its structured result, not the underlying secret.
For reliable operation, start with the narrowest action that satisfies the task, resolve stable provider identifiers before changing state, and validate the returned object or status after execution. Availability still depends on the connected Canny account, granted provider permissions, workspace policy, region, plan, and upstream API behavior.
VERIFIED ACTION SAMPLE
Real Canny capabilities.
Showing 11 of 11 actions. Risk labels are conservative signals based on operation names, not substitutes for provider documentation or runtime policy.
list_boardsREADList all Canny boards available to the authenticated workspace.
create_commentWRITECreate a new Canny comment on a post or as a reply to a comment.
INPUTS: postID / authorID / value / parentID / internal
create_or_update_userWRITECreate a new Canny user or update an existing one by id, userID, or email.
INPUTS: name / alias / created / avatarURL / companies
create_postWRITECreate a new Canny post on a board for a specific author.
INPUTS: boardID / title / details / authorID / byID
list_commentsREADList Canny comments with optional filtering and pagination.
INPUTS: postID / boardID / authorID / companyID / limit
list_postsREADList Canny posts with optional filtering, search, sorting, and pagination.
INPUTS: boardID / authorID / companyID / search / sort
list_usersREADList Canny users with cursor-based pagination.
INPUTS: limit / cursor
retrieve_boardREADRetrieve a single Canny board by board ID.
INPUTS: boardID
retrieve_postREADRetrieve a single Canny post by post ID.
INPUTS: postID
retrieve_userREADRetrieve a single Canny user by id, userID, or email.
INPUTS: id / userID / email
update_postWRITEUpdate mutable fields on an existing Canny post.
INPUTS: postID / title / details / eta / etaPublic
INPUT CONTRACTS
Know what the action needs before it runs.
create_comment
postIDREQUIRED- Unique identifier of the post.
authorIDREQUIRED- Unique identifier of the author.
valueOPTIONAL- Text content of the comment.
parentIDOPTIONAL- Parent comment ID when creating a reply.
internalOPTIONAL- Whether the comment is internal only.
create_or_update_user
nameREQUIRED- Display name of the user.
aliasOPTIONAL- Alias for the user.
createdOPTIONAL- ISO 8601 timestamp from the source system.
avatarURLOPTIONAL- Avatar URL for the user.
companiesOPTIONAL- Companies associated with the user.
create_post
boardIDREQUIRED- Unique identifier of the board.
titleREQUIRED- Title of the post.
detailsREQUIRED- Detailed body of the post.
authorIDREQUIRED- Unique identifier of the author.
byIDOPTIONAL- Admin authoring the post on behalf of the user.
list_comments
postIDOPTIONAL- Unique identifier of the post.
boardIDOPTIONAL- Unique identifier of the board.
authorIDOPTIONAL- Unique identifier of the author.
companyIDOPTIONAL- Unique identifier of the company.
limitOPTIONAL- Maximum number of items to return.
PROVIDER-SPECIFIC WORKFLOWS
Jobs this Agent App can support
Inspect List Boards
List all Canny boards available to the authenticated workspace. Use this as a bounded discovery step, retain the returned identifier, and avoid expanding the read beyond the task's stated scope.
list_boardsControl Create Comment
Create a new Canny comment on a post or as a reply to a comment. Resolve the target first, present material changes for confirmation, and make retries idempotent where the provider supports it.
create_commentVerify with List Comments
List Canny comments with optional filtering and pagination. Compare the returned provider state with the intended outcome and preserve stable IDs or canonical links in the run record.
list_commentsSAFETY BOUNDARY
Operate Canny with explicit limits
- Authorize Canny with API key and grant only the provider access required by the selected actions.
- 4 actions are change-capable by name. Confirm the target identity and material parameters before allowing a write.
- Do not infer permission from catalog visibility. Workspace policy, connection identity, and upstream authorization still govern execution.
- No provider scope string is declared on the sampled actions. Verify the connected account's actual permissions in Canny rather than assuming unrestricted access.
- After a call, inspect the structured result and execution record before reporting that the Canny task completed successfully.
CONNECTION MODEL
API key
Canny secret API key sent as the apiKey POST parameter. Find it in your Canny company settings.
Working Machines stores provider credentials behind the execution boundary. An agent can use an authorized connection identity, but catalog discovery alone does not reveal OAuth tokens, API keys, or provider secrets.
- READ SIGNALS
- 7
- WRITE SIGNALS
- 4
- HIGH IMPACT
- 0
- REVIEW SIGNALS
- 0
EVIDENCE AND AVAILABILITY
Provider reference
Action names, input fields, authentication types, and counts on this page are generated from the Working Machines provider catalog. Provider behavior, quotas, object semantics, account eligibility, and regional availability remain governed by Canny.