Bugherd for AI agents

BugHerd is a visual bug tracker that lets clients and teams pin feedback directly onto a live website, turning each comment into a task on a board. 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.

Project managementAPI keyMCP + RESTbugherd.com
AUDIT LOG · BUGHERDPOLICY: acme-support
09:41:07 · claude · u_8f2read
bugherd.list_users
List Users✓ allowed · 212ms
09:41:08 · claude · u_8f2read
bugherd.show_column
Show Column✓ allowed · 164ms
09:41:09 · claude · u_8f2write
bugherd.create_task
Create Task✓ approved · approved by user
09:41:12 · claude · u_8f2destructive
bugherd.delete_project
Delete Project✕ blocked · policy: deny
EVERY BUGHERD CALL, ON THE RECORD
01 · USE CASES

What agents do in Bugherd.

01

Turn feedback into a task

Turn a piece of client feedback into a task on a project board, ready for a developer to pick up.

02

Add a comment to a task

Post a comment on an existing task to log new context without leaving the board.

03

Confirm before deleting a project

Check a project's details and confirm before deleting it, since its tasks and history go with it.

02 · ACTIONS

26 Bugherd actions, graded by risk.

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

read

13

Look things up. Allowed by default.

  • bugherd.list_users
    List Users
  • bugherd.list_columns
    List Columns
  • bugherd.list_projects
    List Projects
  • bugherd.list_webhooks
    List Webhooks
  • bugherd.list_attachments
    List Attachments
  • bugherd.list_project_tasks
    List Project Tasks
  • bugherd.list_active_projects
    List Active Projects
  • bugherd.show_column
    Show Column
  • bugherd.show_project
    Show Project Details
  • bugherd.show_attachment
    Show Attachment
  • bugherd.show_user_tasks
    Show User Tasks
  • bugherd.show_organization
    Show Organization
  • bugherd.show_user_projects
    Show User Projects

write

12

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

  • bugherd.create_task
    Create Task
  • bugherd.update_task
    Update Task
  • bugherd.create_column
    Create Column
  • bugherd.update_column
    Update Column
  • bugherd.create_comment
    Create Comment
  • bugherd.create_project
    Create Project
  • bugherd.create_webhook
    Create Webhook
  • bugherd.update_project
    Update Project
  • bugherd.create_attachment
    Create Attachment
  • bugherd.add_guest_to_project
    Add Guest to Project
  • bugherd.add_member_to_project
    Add Member to Project
  • bugherd.upload_attachment
    Upload Attachment

destructive

1

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

  • bugherd.delete_project
    Delete Project
03 · HOW IT WORKS

Bugherd in three steps.

  1. 01Your users connect BugherdThey add their Bugherd api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, writes like “create Task” can wait for the user, and “delete Project” can be denied outright.
  3. 03Any agent can actYour agent calls Bugherd 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('bugherd', {
  read: 'allow',
  write: 'ask',        // create_task
  destructive: 'deny',  // delete_project
})

# 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 Bugherd connects.

Users add their Bugherd 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 Bugherd 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 Bugherd from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
07 · FAQ

Bugherd and Arc0, answered.

Q01

Can I use Bugherd with Claude, ChatGPT or Cursor?

Yes. Connect Bugherd 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 Bugherd actions you allow.

Q02

How do users connect Bugherd?

Users add their Bugherd 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 Bugherd actions can my agent take?

26 in total: 13 read, 12 write and 1 destructive, such as “create Task”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in Bugherd?

Yes. Actions like “delete Project” 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 Bugherd too?

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

Get started

Plug Bugherd into your agent.

Your users connect Bugherd once, under your brand. Your agent gets 26 actions behind your policies, with every call on the record.

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