Call automations.run
'run the welcome automation now', 'kick off the onboarding automation for this lead' — start a live run of one switched-on automation in this workspace, named by its board_id (automations.list gives each one): the same run its board's Run now starts, on the version that is live, so its sends and actions are real. It answers at once with the run id and pending; the run continues in the background and the automation's board shows how it went. Pass input to give the run its opening values, and a request_id of your own so a retried call answers the first run instead of starting a second. A draft or a switched-off automation is refused and nothing runs. Each run uses model and step time and is billed as a run. Not for trying a draft safely against the workspace's test contact — that is automations.test_run.
Every result names the workspace it ran in. Say which workspace the answer is about. When the account has more than one workspace and none is selected, this tool refuses with workspace_ambiguous and lists the choices — offer them, never pick one.
Request
- Base URL: https://app.goosybear.ai
- URL: https://app.goosybear.ai/api/v1/tools/automations.run
- Auth: HTTP bearer
Headers
Your own id for this request, echoed back and recorded on the audit trail. 1–128 characters from A–Z a–z 0–9 . _ : -, starting with a letter or digit; anything else is replaced by a generated id.
Request body
Response
The call was admitted and dispatched. ok says whether the tool succeeded — a refusal the tool itself produced is still a 200, exactly as it is a successful JSON-RPC result over MCP.
Changes
No recorded changes to this operation across all 4 revisions of this API.