Search companies

You are wiring up the agntdata "Lead APIs" API to use this endpoint: Search 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_search
   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/search
     Header: Authorization: Bearer <YOUR_AGNTDATA_API_KEY>
   Required parameters:
    - (none)
   Optional parameters:
    - filters (object, optional) — Filter object. Each entry is keyed by filter name and takes either `{ include?: string[], exclude?: string[] }` for categorical filters or `{ min?, max? }` for ranges. Searches that contain ONLY `exclude` filters are rejected — always pair with at least one positive filter. Common keys: `company_industry` ({ include/exclude } — e.g. `{ "include": ["Software Development"] }`); `company_headcount` ({ min, max } — numeric employee count range, e.g. `{ "min": 1000 }`); `company_country` ({ include/exclude } — ISO country names or codes); `company_funding` ({ stage: string[], funding_date: number-of-days, last_funding: { min, max }, total_funding: { min, max } }; amounts use suffix notation like "1M", "10M", "100M"); `company_type` ({ include/exclude } — e.g. ["Privately Held", "Public Company"]). For convenience, flat aliases are accepted and translated server-side: `industry`/`industries` → `company_industry.include`, `country`/`countries` → `company_country.include`, `headcount_min`/`headcount_max` → `company_headcount.{min,max}`. Top-level keys other than `filters`/`page` (e.g. `limit`) are ignored. Example: `{ "company_industry": { "include": ["Software Development"] }, "company_headcount": { "min": 1000 } }`.
    - page (integer, optional) — Page number (25 results per page; max page = 1000).
    - max_cost_cents (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_search), 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_search.md

{
  "name": "companies_search",
  "description": "Search the company graph using structured filters (industry, headcount, location, technology, …). Returns paginated company summaries.",
  "parameters": {
    "type": "object",
    "properties": {
      "filters": {
        "type": "object",
        "additionalProperties": {},
        "description": "Filter object. Each entry is keyed by filter name and takes either `{ include?: string[], exclude?: string[] }` for categorical filters or `{ min?, max? }` for ranges. Searches that contain ONLY `exclude` filters are rejected — always pair with at least one positive filter. Common keys: `company_industry` ({ include/exclude } — e.g. `{ \"include\": [\"Software Development\"] }`); `company_headcount` ({ min, max } — numeric employee count range, e.g. `{ \"min\": 1000 }`); `company_country` ({ include/exclude } — ISO country names or codes); `company_funding` ({ stage: string[], funding_date: number-of-days, last_funding: { min, max }, total_funding: { min, max } }; amounts use suffix notation like \"1M\", \"10M\", \"100M\"); `company_type` ({ include/exclude } — e.g. [\"Privately Held\", \"Public Company\"]). For convenience, flat aliases are accepted and translated server-side: `industry`/`industries` → `company_industry.include`, `country`/`countries` → `company_country.include`, `headcount_min`/`headcount_max` → `company_headcount.{min,max}`. Top-level keys other than `filters`/`page` (e.g. `limit`) are ignored. Example: `{ \"company_industry\": { \"include\": [\"Software Development\"] }, \"company_headcount\": { \"min\": 1000 } }`."
      },
      "page": {
        "type": "integer",
        "exclusiveMinimum": 0,
        "minimum": 0,
        "description": "Page number (25 results per page; max page = 1000)."
      },
      "max_cost_cents": {
        "type": "number",
        "minimum": 0
      }
    },
    "required": []
  }
}