MCP tool
cascades_get_execution
Fetch a single cascade execution by id to check its status and results. Use this to poll after cascades_trigger_workflow until the run reaches a terminal status, and to read the decision: with full read access the response includes `step_outputs` (the per-step results) and `input_context`. Statuses: queued / pending / running / waiting / awaiting_review / completed / failed / cancelled / skipped.
REST operation
This tool makes one call:
GET
/api/v1/executions/{id}
— see getExecution in the API reference for the full response schema and error codes.
Input schema
| Argument | Type | Description |
|---|---|---|
execution_id
required
|
integer |
Execution id. Scoped to the calling api_client; a foreign id returns `404`. |
environment
|
string |
Target environment: "prod" (default) or "dev".
One of:
dev prod |
Example
What the model sends, and the JSON the tool returns (the REST response, verbatim).
Call
{
"name": "cascades_get_execution",
"arguments": {
"execution_id": 4821
}
}Result
{
"data": {
"id": 4821,
"object": "execution",
"workflow_id": 157,
"status": "completed",
"decision": "approve",
"step_outputs": {
"credit": {
"score": 712
},
"decision": {
"outcome": "approve"
}
}
}
}