Integration · Developer tools

Connect Claude & ChatGPT to BugBug

Ask your AI which BugBug tests failed last night, or have it start a suite run against your staging URL. It can read test runs step by step with errors and screenshots, list suites and run profiles, and create or update tests and suites. You get answers about your test results without opening the dashboard.

Connect BugBug free

Free plan, no credit card. Takes about a minute.

Try asking

“Which tests failed in the last suite run?”
The AI lists recent suite runs, opens the latest one and shows each test's result, with the failed ones first.
“Run the Checkout suite against https://staging.example.com.”
It finds the suite, starts a cloud run with that base URL and reports the status when you ask.
“Why did the Login test fail?”
It reads the test run with its step results and errors, and lists the screenshots captured during the run.

What your AI can do

Run tests and suites

Start cloud runs of single tests or whole suites, with a run profile, base URL and variables, and stop them if needed.

Results and screenshots

Read test and suite runs with step results, errors and captured screenshots, filtered by status or date.

Tests and suites

Search tests and suites, browse folders, run profiles and variables, and create or update tests and suites.

“Show me every test in the Payments folder with its last result.”
It finds the folder and searches its tests with the latest run result included.
“Create a suite called Smoke with the Login and Signup tests.”
It looks up the run profiles and the two tests, then creates the suite with the profile you choose.
“Stop the suite run that is still going.”
It finds the running suite run and stops it.

23 tools for BugBug

These tools are switched on when you connect. You can switch any of them off, or require your approval before it runs.

create_suiteChanges dataCreate a test suite with a `name`, a `run_profile_id` and the `tests` it should include.
create_testChanges dataCreate a new, empty test with a `name`, optional notes and folder.
get_suiteGet one suite by `unit_id`, including its tests and settings.
get_suite_runGet full details of a suite run by `suiterun_id`, including the result of each test.
get_suite_run_statusGet the current status of a suite run by `suiterun_id`.
get_testGet one test by `test_id`, including its steps and settings.
get_test_runGet full details of a test run by `testrun_id`, including step results and errors.
get_test_run_statusGet the current status of a test run by `testrun_id` (running, passed, failed).
list_foldersList test or suite folders, filtered by `kind`, name `query` or parent folder.
list_projectsList the BugBug projects the token can see, optionally filtered by name with `query`.
list_run_profilesList the project's run profiles. Use a profile id as `run_profile_id` when running tests or suites.
list_suite_runsList suite runs, filtered by `suite_id`, `status` or start date range.
list_suitesList test suites, optionally filtered by name with `query`. Set `latest_run` to include each suite's last run.
list_test_run_screenshotsList the screenshots captured during a test run by `testrun_id`.
list_test_runsList test runs, filtered by `test_id`, `status` or start date range.
list_variablesList the project's variables that tests can use.
run_suiteChanges dataStart a cloud run of a whole suite by `suite_id`; optional `base_url`, `run_profile_id` and variables. Check progress with get_suite_run_status.
run_testChanges dataStart a cloud run of one test by `test_id`; optional `run_profile_id` and variables. Check progress with get_test_run_status.
search_testsSearch tests by name (`query`) or folder. Set `latest_run` to include each test's last run result.
stop_suite_runChanges dataStop a running suite run by `suiterun_id`.
stop_test_runChanges dataStop a running test run by `testrun_id`.
update_suiteChanges dataChange a suite's name, notes, tests or run settings by `unit_id`.
update_testChanges dataRename a test or change its notes, folder or screen size by `test_id`.

Set up in three steps

1
Pick the app
Create a free PipMCP account and choose BugBug from the app list.
2
Paste your key
Paste your BugBug project API token. In BugBug, open the Integrations page, choose the API tab and copy the project API token. The token belongs to one project, and BugBug's Public API needs a paid BugBug plan.
3
Add the link to your AI
You get a personal MCP link. Add it to Claude, ChatGPT or Cursor:
1. Click your name, then Settings › Connectors › Add custom connector.
2. Paste your link as the Remote MCP server URL.
3. Switch it on from the + menu in a chat.

Questions

What can the AI do in BugBug?

It can read projects, tests, suites, folders, run profiles, variables, test runs, suite runs and run screenshots. It can start and stop test and suite runs in the cloud, create empty tests and new suites, and update the name, notes, folder or settings of tests and suites.

Does the AI see my BugBug API token?

No. Your BugBug token is encrypted at rest and never shown to the AI. After you save it, it is not shown again, not even to you. The AI only sees the results of the tools it calls.

Can I control what the AI is allowed to do?

Yes. You choose which tools are switched on, so you can start with results only. Starting or stopping runs and changing tests or suites can require your approval before they run. Every tool call is logged.

Does it work with ChatGPT?

Yes. In ChatGPT go to Settings › Apps & Connectors › Advanced and turn on Developer mode, then add your PipMCP link. Developer mode needs a paid ChatGPT plan: Plus, Pro, Business or Enterprise. The same link also works in Claude (Settings › Connectors › Add custom connector), Cursor and other MCP clients.

What does it cost?

PipMCP has a free plan with no credit card required. Paid plans bill per completed task. You also need your own BugBug account, and BugBug's Public API needs a paid BugBug plan.

Can the AI record test steps?

No. The AI can create a new, empty test with a name, notes and folder, and change a test's settings. Steps are recorded in BugBug itself. The AI can read a test's existing steps and run it.