Run an agent automation now
run_agent_automation
Starts one run of an agent automation on a site, outside its schedule.
The run starts now and does not move the schedule. Its report is emailed to the person who set the automation up when the run finishes, and list_agent_automation_runs follows it. Each run counts toward the site's 10 runs in a UTC day. It is refused while the automation is off, while a run of it is going, while the site is locked, when the workspace has used its credits, and when the site has used its runs for the day. See Agents.
Request
Call it with a POST to https://api.modulify.ai/v1/run_agent_automation, sending the inputs below as a JSON object. The token needs the config:write scope.
It makes changes, so send an Idempotency-Key header whenever you might retry it. A retry with the same key gets the first answer back instead of running again.
curl -X POST https://api.modulify.ai/v1/run_agent_automation \
-H "Authorization: Bearer YOUR_TOKEN" \
-H "Content-Type: application/json" \
-d '{"projectId":"PROJECT_ID","automationId":"AUTOMATION_ID"}'Over MCP, the same method is the run_agent_automation tool.
Inputs
| Input | Type | Required | Description |
|---|---|---|---|
projectId |
string | Yes | The site id. |
automationId |
string | Yes | The automation id from list_agent_automations. |
Response
Every call answers with the JSON envelope of success, message, data, code and version. data holds the result described above, and on a method that returns a total, count carries it. The response headers carry the call's X-Request-Id and what is left of your per-minute budget in X-RateLimit-Limit, X-RateLimit-Remaining and X-RateLimit-Reset. Errors explains every status code a call can answer with.