Bugbug for AI agents
BugBug is a low-code tool for automating web app tests, letting a team run test suites against a build without maintaining a dedicated QA engineering team. 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 Bugbug.
Run a test against a build
Trigger a specific test to run against the current build and get back a pass or fail.
Check a test run before release
Look up a completed test run's details before deciding a build is safe to ship.
Review a suite's coverage
List the tests inside a suite to see what's covered before adding new ones.
4 Bugbug actions, graded by risk.
Every Bugbug action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
3Look things up. Allowed by default.
- bugbug.list_testsList tests
- bugbug.list_suitesList suites
- bugbug.get_test_run_detailsGet test run details
write
1Create and change things. Allow, or ask the user first.
- bugbug.run_testRun test
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Bugbug in three steps.
- 01Your users connect BugbugThey add their Bugbug api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “run test” can wait for the user to approve.
- 03Any agent can actYour agent calls Bugbug through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('bugbug', { read: 'allow', write: 'ask', // run_test destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Bugbug connects.
Users add their Bugbug 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 Bugbug 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 Bugbug from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Bugbug and Arc0, answered.
Can I use Bugbug with Claude, ChatGPT or Cursor?
Yes. Connect Bugbug 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 Bugbug actions you allow.
How do users connect Bugbug?
Users add their Bugbug 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 Bugbug actions can my agent take?
4 in total: 3 read, 1 write and 0 destructive, such as “run test”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Bugbug?
Yes. Allow read actions and deny writes in the Bugbug policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Bugbug too?
Yes. The same Bugbug connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Bugbug into your agent.
Your users connect Bugbug once, under your brand. Your agent gets 4 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan