run_eval

Active

declared in 1.0.0

Run a single eval scenario (eval_id) or every scenario for an agent (agent_id) against its live Vapi assistant and grade the result. Bills Vapi compute. Mirrors POST /api/v1/evals/run.

Parameters schema

{
  "type": "object",
  "properties": {
    "wait": {
      "type": "boolean",
      "description": "Block until the run completes (default true)."
    },
    "eval_id": {
      "type": "string",
      "description": "Run a single eval scenario by ID."
    },
    "agent_id": {
      "type": "string",
      "description": "Run every eval scenario for this agent."
    },
    "max_wait_ms": {
      "type": "integer",
      "description": "Per-run wait cap in ms when wait is true (default 60000, max 110000)."
    }
  }
}

What this tool wraps· 0 endpoints

min confidence0.70 0.50

No endpoints wrapped at confidence ≥ 0.70.

Parent server

KaiCalls

https://github.com/cgallic/kai_calls

1/7 registries

View full server →