queue_discovered

Inputs

{
  "type": "object",
  "properties": {
    "run_id": {
      "type": "string",
      "pattern": "^[A-Za-z0-9_-]{1,150}$"
    },
    "keys": {
      "type": "array",
      "minItems": 1,
      "maxItems": 10,
      "items": {
        "type": "string",
        "pattern": "^[A-Za-z0-9_-]{1,100}$"
      }
    },
    "user_intent_token": {
      "type": "string",
      "minLength": 1,
      "maxLength": 256
    }
  },
  "additionalProperties": false,
  "required": [
    "run_id",
    "keys"
  ]
}

Outputs and behavior

Enqueue selected saved discovery candidates for normal capture. Use after discover_candidates returns a run and candidate keys; use that tool again to search for new candidates. Requires agent discovery consent or a dashboard intent; stdio needs agent consent because dashboard intents are process-bound. Returns queued and skipped picks, skipping unknown, unsupported, captured or queued URLs. No ScrapeCreators credits are spent; the resident retry worker performs capture later.

The registry does not publish an output schema for this tool. The description above is its documented behavior; response fields beyond it are not specified here.

Example call

Example tool name and arguments, generated from the input schema. Replace placeholder strings and sample numbers with your own values. This is a request template, not a recorded call or response.

{
  "name": "queue_discovered",
  "arguments": {
    "run_id": "YOUR_RUN_ID",
    "keys": [
      "YOUR_KEYS"
    ]
  }
}

Clients

This tool is available to MCP clients using stdio or http.

The registry records transport support, not individual client test results. See the MCP setup reference for named clients, configuration, and tool-list limits.