Referring domains for a target

You are wiring up the superagnt "SEO" API to use this endpoint: Referring domains for a target.

1. CONNECT over MCP (preferred). No token to paste either way.
   On Claude (claude.ai, the desktop app, or Claude Code signed in with a Claude
   account), the server is a connector: give the user this link, they click Add
   and approve:
     https://claude.ai/customize/connectors/yours?modal=add-custom-connector&connectorName=superagnt&connectorUrl=https%3A%2F%2Fmcp.superagnt.com%2Fmcp&open_in_browser=1
   Any other MCP client (or Claude Code signed in with an API key): add the server
   and let the client run the browser sign-in:
     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_referring_domains
   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.superagnt.com/referring-domains
     Header: Authorization: Bearer <YOUR_AGNTDATA_API_KEY>
   Required parameters:
    - target (string, required) — Domain, subdomain or full page URL to list referring domains for.
   Optional parameters:
    - limit (integer, optional) — Max referring domains to return. Default 100. Cost scales with rows.
    - offset (integer, optional) — Pagination offset.
    - exclude_internal_backlinks (boolean, optional) — Ignore links from the target to itself. Default true.
    - filters (array, optional) — Optional filter expression as [field, operator, value] triples. Operators: =, <>, <, <=, >, >=, in, not_in, like, not_like. Recipe: [["rank",">",100]] keeps stronger referring domains (rank is the referring domain's authority, higher is better).
    - order_by (array, optional) — Sort rules, e.g. ["rank,desc"].

3. COST & KEY. This endpoint is metered — pricing varies by request, from $0.05 per call. Only successful calls are charged.
   Get a superagnt API key at https://app.superagnt.com.

4. TEST. Connect the server (or set the key), discover the tool
   (data_seo_referring_domains), 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://www.superagnt.com/docs/apis/seo/endpoints/referring_domains.md

{
  "name": "referring_domains",
  "description": "Lists the domains linking to a target, each with rank, backlink count, first/last seen dates and spam score. This is the outreach-prospecting call: the sites already linking to a competitor are the sites most likely to link to you. Cost scales with rows; default 100 is right for most pulls.",
  "parameters": {
    "type": "object",
    "properties": {
      "target": {
        "type": "string",
        "description": "Domain, subdomain or full page URL to list referring domains for."
      },
      "limit": {
        "type": "integer",
        "minimum": 1,
        "maximum": 1000,
        "default": 100,
        "description": "Max referring domains to return. Default 100. Cost scales with rows."
      },
      "offset": {
        "type": "integer",
        "minimum": 0,
        "description": "Pagination offset."
      },
      "exclude_internal_backlinks": {
        "type": "boolean",
        "default": true,
        "description": "Ignore links from the target to itself. Default true."
      },
      "filters": {
        "type": "array",
        "items": {},
        "description": "Optional filter expression as [field, operator, value] triples. Operators: =, <>, <, <=, >, >=, in, not_in, like, not_like. Recipe: [[\"rank\",\">\",100]] keeps stronger referring domains (rank is the referring domain's authority, higher is better)."
      },
      "order_by": {
        "type": "array",
        "items": {
          "type": "string"
        },
        "description": "Sort rules, e.g. [\"rank,desc\"]."
      }
    },
    "required": [
      "target"
    ]
  }
}