Get started

Canny for AI agents

Canny collects and prioritizes customer feedback, letting a product team turn scattered feature requests into a ranked, trackable roadmap for planning. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.

Connect CannySee the 25 actions ↓
Project managementAPI keyMCP + RESTcanny.io
AUDIT LOG · CANNYPOLICY: acme-support
09:41:07 · claude · u_8f2read
canny.list_tags
List Tags✓ allowed · 212ms
09:41:08 · claude · u_8f2read
canny.list_posts
List Posts✓ allowed · 164ms
09:41:09 · claude · u_8f2write
canny.create_tag
Create Tag✓ approved · approved by user
09:41:12 · claude · u_8f2destructive
canny.delete_post
Delete Post✕ blocked · policy: deny
EVERY CANNY CALL, ON THE RECORD
01 · USE CASES

What agents do in Canny.

01

Create a feedback post

Create a new post capturing a customer's feature request on the right board.

02

Move a post's status forward

Change a post's status from planned to in progress once work actually starts.

03

Confirm before deleting a post

Confirm before deleting a feedback post, since its votes and comments disappear along with it.

02 · ACTIONS

25 Canny actions, graded by risk.

Every Canny action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

12

Look things up. Allowed by default.

  • canny.list_tags
    List Tags
  • canny.list_posts
    List Posts
  • canny.list_users
    List Users
  • canny.list_votes
    List Votes
  • canny.list_boards
    List Boards
  • canny.list_comments
    List Comments
  • canny.list_companies
    List Companies
  • canny.list_categories
    List Categories
  • canny.list_opportunities
    List Opportunities
  • canny.retrieve_tag
    Retrieve Tag
  • canny.retrieve_user
    Retrieve User
  • canny.retrieve_board
    Retrieve Board

write

9

Create and change things. Allow, or ask the user first.

  • canny.create_tag
    Create Tag
  • canny.create_post
    Create Post
  • canny.create_vote
    Create Vote
  • canny.update_post
    Update Post
  • canny.add_post_tag
    Add Post Tag
  • canny.create_comment
    Create Comment
  • canny.create_or_update_user
    Create or Update User
  • canny.create_changelog_entry
    Create Changelog Entry
  • canny.change_post_status
    Change Post Status

destructive

4

Delete, cancel or archive. Ask first, or deny outright.

  • canny.delete_post
    Delete Post
  • canny.delete_user
    Delete User
  • canny.delete_vote
    Delete Vote
  • canny.delete_comment
    Delete Comment
03 · HOW IT WORKS

Canny in three steps.

  1. 01Your users connect CannyThey add their Canny api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, writes like “create Tag” can wait for the user, and “delete Post” can be denied outright.
  3. 03Any agent can actYour agent calls Canny through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
POLICY.TS
await arc0.policies.set('canny', {
  read: 'allow',
  write: 'ask',        // create_tag
  destructive: 'deny',  // delete_post
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2
04 · AUTH AND DATA

How Canny connects.

Users add their Canny api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

The same Canny connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →

AUTH
API key
CREDENTIALS
Per-tenant encrypted vault
MODEL SEES
Results only, never credentials
AUDIT LOG
Every call, on every plan
05 · WORKS WITH

Use Canny from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
06 · RELATED

More project management apps.

Linear48 actionsJira103 actionsAsana153 actionsTrello330 actionsMonday126 actionsGoogle Tasks18 actionsMoco218 actionsWrike144 actions
ALL PROJECT MANAGEMENT APPS →
07 · FAQ

Canny and Arc0, answered.

Q01

Can I use Canny with Claude, ChatGPT or Cursor?

Yes. Connect Canny to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Canny actions you allow.

Q02

How do users connect Canny?

Users add their Canny api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

Q03

Which Canny actions can my agent take?

25 in total: 12 read, 9 write and 4 destructive, such as “create Tag”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in Canny?

Yes. Actions like “delete Post” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.

Q05

Can my own backend call Canny too?

Yes. The same Canny connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug Canny into your agent.

Your users connect Canny once, under your brand. Your agent gets 25 actions behind your policies, with every call on the record.

Connect CannyBrowse all apps →

Free to build · MCP + REST · Audit log on every plan