How often LLMs mention a domain

You are wiring up the agntdata "SEO" API to use this endpoint: How often LLMs mention a domain.

1. CONNECT over MCP (preferred). Add the superagnt MCP server, then let the client
   run OAuth on first tool call — no token to paste:
     claude mcp add --scope user --transport http superagnt https://mcp.superagnt.com/mcp
     claude mcp login superagnt
   MCP endpoint: https://mcp.superagnt.com/mcp
   After connecting, the tool you want is named exactly:
     data_seo_ai_visibility
   Call agnt_tools_search or agnt_tools_list_enabled to confirm it is available.

2. REST fallback (if you are not using MCP):
     POST https://api.agntdata.dev/ai-visibility
     Header: Authorization: Bearer <YOUR_AGNTDATA_API_KEY>
   Required parameters:
    - (none)
   Optional parameters:
    - targets (array, optional) — Domains to measure LLM mention metrics for, no protocol. Pass at least one of targets or keywords.
    - keywords (array, optional) — Keyword phrases to measure LLM mention metrics for, as an alternative or addition to domains.
    - limit (integer, optional) — Max rows to return. Default 100. Cost scales with rows.

3. COST & KEY. This endpoint is priced per call in credits, and each successful response reports its own cost in its meta.costCents field. Only successful calls are charged.
   Get an agntdata API key at https://app.agntdata.dev.

4. TEST. Connect the server (or set the key), discover the tool
   (data_seo_ai_visibility), run one minimal call with just the required parameters,
   and report back the shape of the JSON response (top-level fields).

Reference (machine-readable variant): https://superagnt.com/docs/apis/seo/endpoints/ai_visibility.md

{
  "name": "ai_visibility",
  "description": "Returns aggregated metrics on how often large language models mention or cite the target domains or keywords in their answers. Navigation: the data lives at result[0].aggregated_metrics (by platform/location/language) — the items array is often legitimately EMPTY, so do not treat items_count 0 as no data. Priced per request (roughly 40x a search, ~18 cents) regardless of returned rows, so run it for periodic brand tracking, not in loops.",
  "parameters": {
    "type": "object",
    "properties": {
      "targets": {
        "type": "array",
        "items": {
          "type": "string"
        },
        "maxItems": 10,
        "description": "Domains to measure LLM mention metrics for, no protocol. Pass at least one of targets or keywords."
      },
      "keywords": {
        "type": "array",
        "items": {
          "type": "string"
        },
        "maxItems": 10,
        "description": "Keyword phrases to measure LLM mention metrics for, as an alternative or addition to domains."
      },
      "limit": {
        "type": "integer",
        "minimum": 1,
        "maximum": 1000,
        "default": 100,
        "description": "Max rows to return. Default 100. Cost scales with rows."
      }
    },
    "required": []
  }
}