find_mentions

Inputs

{
  "type": "object",
  "properties": {
    "match": {
      "type": "string",
      "enum": [
        "forgiving",
        "strict"
      ],
      "default": "forgiving",
      "description": "Forgiving matches entity name words; strict requires the exact normalized name."
    },
    "entity": {
      "type": "string",
      "description": "Entity name to look up (case-insensitive)."
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 200,
      "default": 50
    }
  },
  "additionalProperties": false,
  "required": [
    "entity"
  ]
}

Outputs and behavior

Find recorded entity-name mentions across saved items, with stored spans, timing and source links. Use for people, products, tools or topics already indexed as entities; use search_clips for arbitrary transcript text or search_uoinks for whole-item search. Ranks by name match with newest first on ties. Results are limited and do not extract new entities.

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": "find_mentions",
  "arguments": {
    "entity": "YOUR_ENTITY",
    "match": "forgiving",
    "limit": 50
  }
}

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.