runs_get

Free tool to get one run's looot status, result and cost once settled, separate from the provider's own response status.

Works in

and any MCP client

Return a run’s looot lifecycle status separately from the provider’s own response status, plus result and cost once settled. Free and read-only. Use it after run when you did not wait, or to re-check a run later. It also follows a workflow run started via run with endpointId: "workflow:<id>", by its returned workflowRunId.

Inputs

Argument	Type	Required	Default	Limits	Meaning
`runId`	string	Yes	-	-	A run id from `run` or `runs_list`.
`fields`	string[]	No	all of `result`	At most 50 paths, 200 characters each	Dotted paths of `result` to keep, for example `items.name`. Lists on a path are walked item by item. A path the result does not have is a `validation_error`.
`max_items`	integer	No	no cap	1 to 10000	Keep only the first N entries of every list in `result`, at any depth.

On a failed run, error carries {code, providerStatus, message, requestId, whoseError, retryable, retryHint}, never secrets or raw provider headers. A completed run can carry an optional normalized object next to result (fixed field names per job); it is absent, never null, when it does not apply.

Both options are optional and only change the copy you get back: the charge, the stored result and a later call without options are the same. When something was cut, the answer carries trimmed: {"truncated": true, "fields": ["items.name"], "max_items": 2, "arrays": [{"path": "$.items", "kept": 2, "total": 40}]}. status, outcome, route, normalized and the cost fields are never trimmed. run accepts the same two arguments; there, an unknown path is listed in trimmed.unmatched and the full result comes back, because the run is already paid. REST: GET /v1/runs/{runId}?fields=items.name&max_items=2.

Example call

{
  "runId": "run_807967cc4b7f468fa5d7dbcaefdee859"
}

Example answer

Abridged: result is the provider’s own payload and varies by endpoint.

{
  "runId": "run_807967cc4b7f468fa5d7dbcaefdee859",
  "endpointId": "linkup-search",
  "status": "completed",
  "providerResponseStatus": "ok",
  "createdAt": "2026-09-24T21:14:36.435Z",
  "startedAt": "2026-09-24T21:14:36.781Z",
  "completedAt": "2026-09-24T21:14:37.377607+00:00",
  "input": {
    "q": "looot api gateway",
    "depth": "standard",
    "outputType": "searchResults"
  },
  "error": null
}

Errors

Free and read-only; no runs.execute needed. A missing runId returns validation_error: Invalid input: expected string, received undefined at runId. An unknown runId in this workspace returns not_found with the id you sent, not a generic lookup failure.

REST and CLI

REST: GET /v1/runs/{runId}
CLI: looot runs get <run-id>