FeedBear for AI agents
FeedBear helps product teams collect and organize customer feedback, feature requests, and changelog updates in one board that customers can see and vote on. 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.
What agents do in FeedBear.
Log a new feature request
Create a board item for a feature request a customer submitted through support.
Check a request's comments
List the comments on a board item to see what customers have said about a request.
Confirm before deleting a board item
Require approval before deleting a board item, since it removes a customer's tracked request and votes.
10 FeedBear actions, graded by risk.
Every FeedBear action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
6Look things up. Allowed by default.
- feedbear.list_boardsList Boards
- feedbear.list_statusesList Statuses
- feedbear.get_board_itemGet Board Item
- feedbear.list_board_itemsList Board Items
- feedbear.list_item_commentsList Item Comments
- feedbear.list_changelog_entriesList Changelog Entries
write
3Create and change things. Allow, or ask the user first.
- feedbear.add_item_commentAdd Item Comment
- feedbear.create_board_itemCreate Board Item
- feedbear.update_board_itemUpdate Board Item
destructive
1Delete, cancel or archive. Ask first, or deny outright.
- feedbear.delete_board_itemDelete Board Item
FeedBear in three steps.
- 01Your users connect FeedBearThey add their FeedBear api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, writes like “create Board Item” can wait for the user, and “delete Board Item” can be denied outright.
- 03Any agent can actYour agent calls FeedBear through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('feedbear', { read: 'allow', write: 'ask', // create_board_item destructive: 'deny', // delete_board_item }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How FeedBear connects.
Users add their FeedBear 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 FeedBear 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
Use FeedBear from any agent.
More project management apps.
FeedBear and Arc0, answered.
Can I use FeedBear with Claude, ChatGPT or Cursor?
Yes. Connect FeedBear 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 FeedBear actions you allow.
How do users connect FeedBear?
Users add their FeedBear 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.
Which FeedBear actions can my agent take?
10 in total: 6 read, 3 write and 1 destructive, such as “create Board Item”. Your policies decide which of them each agent may call.
Can I stop my agent from deleting things in FeedBear?
Yes. Actions like “delete Board Item” 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.
Can my own backend call FeedBear too?
Yes. The same FeedBear connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug FeedBear into your agent.
Your users connect FeedBear once, under your brand. Your agent gets 10 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan