Discover companies

You are wiring up the agntdata "Lead APIs" API to use this endpoint: Discover 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_discover
   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/discover
     Header: Authorization: Bearer <YOUR_AGNTDATA_API_KEY>
   Required parameters:
    - (none)
   Optional parameters:
    - query (string, optional) — Free-text query (e.g. "AI startups in healthcare"). Combine with `filters` or use alone.
    - filters (object, optional) — Filter object. Supported keys (each is an array unless noted): `industries` (array of industry strings — e.g. ["Computer Software", "Internet"]); `headcount` (string range bucket — one of "1-10", "11-50", "51-200", "201-500", "501-1000", "1001-5000", "5001-10000", "10001+"); `company_type` (array — e.g. ["educational", "government", "nonprofit", "private", "public", "self_employed"]); `technology` (array of technology slugs — e.g. ["stripe", "salesforce"]); `country` (array of ISO-3166 alpha-2 codes — e.g. ["US", "GB"]). Use the keys above exactly as written; flat aliases like `industry` (singular), `headcount_min`, or `headcount_max` are ignored and yield empty results. Example: `{ "industries": ["Computer Software"], "headcount": "1001-5000", "country": ["US"] }`.

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_discover), 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_discover.md

{
  "name": "companies_discover",
  "description": "Find companies matching a set of criteria. Pass either a natural-language `query` or structured `filters` (industry, headcount, location, technology, funding, keywords, …). Returns paginated company summaries.",
  "parameters": {
    "type": "object",
    "properties": {
      "query": {
        "type": "string",
        "minLength": 1,
        "description": "Free-text query (e.g. \"AI startups in healthcare\"). Combine with `filters` or use alone."
      },
      "filters": {
        "type": "object",
        "additionalProperties": {},
        "description": "Filter object. Supported keys (each is an array unless noted): `industries` (array of industry strings — e.g. [\"Computer Software\", \"Internet\"]); `headcount` (string range bucket — one of \"1-10\", \"11-50\", \"51-200\", \"201-500\", \"501-1000\", \"1001-5000\", \"5001-10000\", \"10001+\"); `company_type` (array — e.g. [\"educational\", \"government\", \"nonprofit\", \"private\", \"public\", \"self_employed\"]); `technology` (array of technology slugs — e.g. [\"stripe\", \"salesforce\"]); `country` (array of ISO-3166 alpha-2 codes — e.g. [\"US\", \"GB\"]). Use the keys above exactly as written; flat aliases like `industry` (singular), `headcount_min`, or `headcount_max` are ignored and yield empty results. Example: `{ \"industries\": [\"Computer Software\"], \"headcount\": \"1001-5000\", \"country\": [\"US\"] }`."
      }
    },
    "required": []
  }
}