View as Markdown

Default model tools

speakers_get_appearances

Get where a person appears

Reads a person's current Recording voices, saved answers with lost placement, and editorial Moments. Each voice carries its current identity state, source timing when available, and the recording_id/speaker_map_id selector for recordings_get_speaker_evidence. Unplaced answers retain their recording_id/decision_id selector when available; no current occurrence or timing is inferred. Sightings are faces currently named as this person, each with its image_answer_id or automatic basis and source seconds. Each recent group reports truncation separately. A suggestion is not an attached person. With project_id, all rows are project-scoped and assignment exceptions are reported separately. Moment rows keep the transcript speaker_label and use current project presentation for display_label. Legacy clips and exports groups are empty; exact finished Export labels are not recalculated.

Surface: Default model and app

Product release eb8538f4a297f331d0399351c1e175bffcd212d2
Public contract commit 20688e11af473a363145ed880d5019c90a7ec1e2
Public contract SHA-256 87a94b85a84dc19245fc03f9b544c70d64bd9f5e08585dcccb38157cace5700d
Captured 2026-10-04T11:55:45.577Z. Review or improve this contract on GitHub.

These blocks show the complete MCP descriptors captured from serving Rails. Security schemes and resource URIs can differ by connected host.

Default model descriptor

{
  "name": "speakers_get_appearances",
  "title": "Get where a person appears",
  "description": "Reads a person's current Recording voices, saved answers with lost placement, and editorial Moments. Each voice carries its current identity state, source timing when available, and the recording_id/speaker_map_id selector for recordings_get_speaker_evidence. Unplaced answers retain their recording_id/decision_id selector when available; no current occurrence or timing is inferred. Sightings are faces currently named as this person, each with its image_answer_id or automatic basis and source seconds. Each recent group reports truncation separately. A suggestion is not an attached person. With project_id, all rows are project-scoped and assignment exceptions are reported separately. Moment rows keep the transcript speaker_label and use current project presentation for display_label. Legacy clips and exports groups are empty; exact finished Export labels are not recalculated.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "speaker_profile_id": {
        "type": "string",
        "description": "Person public ID, slug, or UUID."
      },
      "status": {
        "type": "string",
        "enum": [
          "all",
          "current",
          "stale"
        ],
        "description": "Optional Moment status filter. Defaults to all. Voices always describe current placements; their standing reports any stale review separately."
      },
      "project_id": {
        "type": "string",
        "description": "Optional project public ID to limit results."
      },
      "limit": {
        "type": "integer",
        "description": "Maximum rows per group. Default 20, maximum 50."
      },
      "cursor": {
        "type": "string",
        "description": "Optional next_cursor from a previous call, to read the next page of voices, saved answers and sightings."
      }
    },
    "required": [
      "speaker_profile_id"
    ],
    "additionalProperties": false
  },
  "annotations": {
    "title": "Get where a person appears",
    "readOnlyHint": true,
    "destructiveHint": false,
    "idempotentHint": true,
    "openWorldHint": false
  },
  "securitySchemes": [
    {
      "type": "noauth"
    }
  ],
  "_meta": {
    "securitySchemes": [
      {
        "type": "noauth"
      }
    ],
    "ui": {
      "visibility": [
        "model",
        "app"
      ]
    },
    "openai/widgetAccessible": true
  }
}

App descriptor

{
  "name": "speakers_get_appearances",
  "title": "Get where a person appears",
  "description": "Reads a person's current Recording voices, saved answers with lost placement, and editorial Moments. Each voice carries its current identity state, source timing when available, and the recording_id/speaker_map_id selector for recordings_get_speaker_evidence. Unplaced answers retain their recording_id/decision_id selector when available; no current occurrence or timing is inferred. Sightings are faces currently named as this person, each with its image_answer_id or automatic basis and source seconds. Each recent group reports truncation separately. A suggestion is not an attached person. With project_id, all rows are project-scoped and assignment exceptions are reported separately. Moment rows keep the transcript speaker_label and use current project presentation for display_label. Legacy clips and exports groups are empty; exact finished Export labels are not recalculated.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "speaker_profile_id": {
        "type": "string",
        "description": "Person public ID, slug, or UUID."
      },
      "status": {
        "type": "string",
        "enum": [
          "all",
          "current",
          "stale"
        ],
        "description": "Optional Moment status filter. Defaults to all. Voices always describe current placements; their standing reports any stale review separately."
      },
      "project_id": {
        "type": "string",
        "description": "Optional project public ID to limit results."
      },
      "limit": {
        "type": "integer",
        "description": "Maximum rows per group. Default 20, maximum 50."
      },
      "cursor": {
        "type": "string",
        "description": "Optional next_cursor from a previous call, to read the next page of voices, saved answers and sightings."
      }
    },
    "required": [
      "speaker_profile_id"
    ],
    "additionalProperties": false
  },
  "annotations": {
    "title": "Get where a person appears",
    "readOnlyHint": true,
    "destructiveHint": false,
    "idempotentHint": true,
    "openWorldHint": false
  },
  "securitySchemes": [
    {
      "type": "noauth"
    }
  ],
  "_meta": {
    "securitySchemes": [
      {
        "type": "noauth"
      }
    ],
    "ui": {
      "visibility": [
        "model",
        "app"
      ]
    },
    "openai/widgetAccessible": true
  },
  "outputSchema": {
    "type": "object",
    "properties": {
      "speaker": {
        "type": "object"
      },
      "status": {
        "type": "string"
      },
      "counts": {
        "type": "object"
      },
      "assignment_review": {
        "type": [
          "object",
          "null"
        ]
      },
      "moments": {
        "type": "array",
        "items": {
          "type": "object"
        }
      },
      "voices": {
        "type": "array",
        "items": {
          "type": "object"
        }
      },
      "voices_has_more": {
        "type": "boolean"
      },
      "unplaced_answers": {
        "type": "array",
        "items": {
          "type": "object"
        }
      },
      "unplaced_answers_has_more": {
        "type": "boolean"
      },
      "sightings": {
        "type": "array",
        "items": {
          "type": "object"
        }
      },
      "sightings_has_more": {
        "type": "boolean"
      },
      "next_cursor": {
        "type": [
          "string",
          "null"
        ]
      },
      "clips": {
        "type": "array",
        "items": {
          "type": "object"
        }
      },
      "exports": {
        "type": "array",
        "items": {
          "type": "object"
        }
      }
    },
    "required": [],
    "additionalProperties": false
  }
}

Live Workspace descriptor

{
  "name": "speakers_get_appearances",
  "title": "Get where a person appears",
  "description": "Reads a person's current Recording voices, saved answers with lost placement, and editorial Moments. Each voice carries its current identity state, source timing when available, and the recording_id/speaker_map_id selector for recordings_get_speaker_evidence. Unplaced answers retain their recording_id/decision_id selector when available; no current occurrence or timing is inferred. Sightings are faces currently named as this person, each with its image_answer_id or automatic basis and source seconds. Each recent group reports truncation separately. A suggestion is not an attached person. With project_id, all rows are project-scoped and assignment exceptions are reported separately. Moment rows keep the transcript speaker_label and use current project presentation for display_label. Legacy clips and exports groups are empty; exact finished Export labels are not recalculated.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "speaker_profile_id": {
        "type": "string",
        "description": "Person public ID, slug, or UUID."
      },
      "status": {
        "type": "string",
        "enum": [
          "all",
          "current",
          "stale"
        ],
        "description": "Optional Moment status filter. Defaults to all. Voices always describe current placements; their standing reports any stale review separately."
      },
      "project_id": {
        "type": "string",
        "description": "Optional project public ID to limit results."
      },
      "limit": {
        "type": "integer",
        "description": "Maximum rows per group. Default 20, maximum 50."
      },
      "cursor": {
        "type": "string",
        "description": "Optional next_cursor from a previous call, to read the next page of voices, saved answers and sightings."
      }
    },
    "required": [
      "speaker_profile_id"
    ],
    "additionalProperties": false
  },
  "annotations": {
    "title": "Get where a person appears",
    "readOnlyHint": true,
    "destructiveHint": false,
    "idempotentHint": true,
    "openWorldHint": false
  },
  "securitySchemes": [
    {
      "type": "noauth"
    }
  ],
  "_meta": {
    "securitySchemes": [
      {
        "type": "noauth"
      }
    ]
  },
  "outputSchema": {
    "type": "object",
    "properties": {
      "speaker": {
        "type": "object"
      },
      "status": {
        "type": "string"
      },
      "counts": {
        "type": "object"
      },
      "assignment_review": {
        "type": [
          "object",
          "null"
        ]
      },
      "moments": {
        "type": "array",
        "items": {
          "type": "object"
        }
      },
      "voices": {
        "type": "array",
        "items": {
          "type": "object"
        }
      },
      "voices_has_more": {
        "type": "boolean"
      },
      "unplaced_answers": {
        "type": "array",
        "items": {
          "type": "object"
        }
      },
      "unplaced_answers_has_more": {
        "type": "boolean"
      },
      "sightings": {
        "type": "array",
        "items": {
          "type": "object"
        }
      },
      "sightings_has_more": {
        "type": "boolean"
      },
      "next_cursor": {
        "type": [
          "string",
          "null"
        ]
      },
      "clips": {
        "type": "array",
        "items": {
          "type": "object"
        }
      },
      "exports": {
        "type": "array",
        "items": {
          "type": "object"
        }
      }
    },
    "required": [],
    "additionalProperties": false
  }
}

Errors

[
  "speaker_not_found",
  "project_not_found",
  "invalid_input"
]

Examples

[]