Use the Speak AI MCP server tool get_automation_run to get one automation run in
full: every step, in dependency order, with what it produced and why it stopped.
What does it do?
Get one automation run in full: every step, in dependency order, with what it
produced and why it stopped. Use this after test_automation or to explain a run
that went the wrong way. On a branched automation the run’s overall status is not
the whole story (a filter that stops one leg marks the entire run “killed” even when
the other leg finished its work) so read the per-step summary this returns, not just
the status.
Parameters
get_automation_run takes 2 parameters, all of them required.
| Name | Type | Required | Description |
|---|---|---|---|
automationId |
string | Yes | Unique identifier of the automation |
runId |
string | Yes | Run id, from get_automation_runs or test_automation |
Behaviour
The Speak AI MCP server publishes these behaviour hints for get_automation_run.
- Only reads data. Does not modify your workspace.
- Does not delete or overwrite existing data.
- Repeating an identical call is safe.
- Stays inside Speak AI. Does not reach other systems.
Related
- Automations lists the rest of the Automations category.
- Tool reference lists every Speak AI MCP server tool.
- MCP server covers setup, supported clients, and what agents can do once connected.