Bulk enrich companies

You are wiring up the agntdata "Lead APIs" API to use this endpoint: Bulk enrich companies.

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_agnt_companies_bulk_enrich
   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/companies/bulk-enrich
     Header: Authorization: Bearer <YOUR_AGNTDATA_API_KEY>
   Required parameters:
    - inputs (array, required)
   Optional parameters:
    - fields (array, optional)
    - max_cost_cents_per_record (number, optional)

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_agnt_companies_bulk_enrich), 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/lead/agnt/endpoints/companies_bulk_enrich.md

{
  "name": "companies_bulk_enrich",
  "description": "Enrich up to 100 companies in one call. Each input must include at least one of: `domain`, `name` (or `company_name`), `linkedin_url` (top-level on the input object — NOT nested under `identifiers` like the single-record endpoint). `domain` is the strongest signal. Each input runs the same field-aware waterfall as `/companies/enrich`. Use `max_cost_cents_per_record` to cap per-record spend.",
  "parameters": {
    "type": "object",
    "properties": {
      "inputs": {
        "type": "array",
        "items": {
          "type": "object",
          "properties": {
            "identifier": {
              "type": "string",
              "minLength": 1,
              "description": "Optional caller-supplied label echoed back in the response — use it to align results to your input rows."
            },
            "domain": {
              "type": "string",
              "minLength": 1,
              "description": "Company root domain (e.g. \"tesla.com\"). Strongest signal."
            },
            "name": {
              "type": "string",
              "minLength": 1,
              "description": "Company name. Use when domain is unknown."
            },
            "company_name": {
              "type": "string",
              "minLength": 1,
              "description": "Alias of `name`."
            },
            "linkedin_url": {
              "type": "string",
              "format": "uri",
              "description": "Full company LinkedIn URL."
            }
          },
          "additionalProperties": false,
          "description": "Each input must include AT LEAST ONE of `domain`, `name`/`company_name`, or `linkedin_url` — top-level on the input object (NOT nested under `identifiers`, which differs from `/companies/enrich`)."
        },
        "minItems": 1,
        "maxItems": 100
      },
      "fields": {
        "type": "array",
        "items": {
          "type": "string",
          "enum": [
            "name",
            "domain",
            "description",
            "industry",
            "employee_count_range",
            "employee_count",
            "hq_location",
            "founded_year",
            "linkedin_url",
            "twitter_url",
            "technologies",
            "funding",
            "competitors"
          ]
        }
      },
      "max_cost_cents_per_record": {
        "type": "number",
        "minimum": 0
      }
    },
    "required": [
      "inputs"
    ]
  }
}