Forager MCP Server

@pipeworx/forager

Find a person's phone number from their LinkedIn profile URL, via Forager (forager.ai). Part of enrich-waterfall's new enrich_find_phone finder rotation (fleet #2860).

Part of Pipeworx — an MCP gateway connecting AI agents to 1865+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

Tools

• forager_find_phone(linkedin_url?, person_id?, _accountId, _apiKey) — phone number + type. Requires BOTH a Forager account id and an API key.

Auth

BYO only. Pass your Forager account id as _accountId and your API key as _apiKey (header X-API-KEY, with the account id as a PATH segment: /api/{account_id}/...). Both are on your Forager dashboard. No platform key (D4).

Data sources

• https://api-v2.forager.ai/api/{account_id}/datastorage/person_contacts_lookup/phone_numbers/

Verification notes (fleet #2860, 2026-10-08, no vendor key held) — THIS PACK HAS THE WEAKEST CONFIRMATION IN THE BATCH

• The URL path is confirmed live. Every auth shape tried against .../phone_numbers/ with account id "0" returns HTTP 403 (never 404), so the path and the account-id-in-path convention are real.
• The header name is NOT independently confirmed. No header, X-API-KEY: invalidkey123, Authorization: Api-Key invalidkey123, and Authorization: Bearer invalidkey123 all return the byte-identical {"detail":"Authentication credentials were not provided."}. A placeholder-key probe cannot tell "wrong header" apart from "right header, garbage key" when the server's generic-scheme message is this generic. X-API-KEY is used here because that is what search results describing Forager's own docs name, but this is the one auth shape in this batch that should be treated as a hypothesis, not a confirmed fact, until a real key either works or returns a DIFFERENT 401/403 body.
• The request/response body fields are a best-effort guess, not a confirmed schema. We could not read docs.forager.ai's own schema page for this specific endpoint (only sibling endpoints — detail lookup, reverse-by-email, reverse-by-phone, role search — turned up in what we could fetch). This pack sends {"linkedin_url": ...} or {"person_id": ...} and reads a phone_numbers array (string or {number, type} objects) back, by analogy with Forager's REST conventions elsewhere. If a real key gets a 200 with a different shape, findPhone() in src/index.ts is the only place that needs fixing.
• Not verified (no key held), and more load-bearing than usual for this pack: the auth header name, the request body field name, the response field name, and whether _accountId is even the right concept (vs. the account id being derivable from the key itself).

Quick Start

Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):

{
  "mcpServers": {
    "forager": {
      "url": "https://gateway.pipeworx.io/forager/mcp"
    }
  }
}

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/forager/mcp returns the tools in the table above plus the shared Pipeworx meta-tools — ask_pipeworx, discover_tools, search_within, remember/recall and the rest of the gateway-wide set. So the tool count you see is larger than this table: a single-pack endpoint currently lists roughly 30 shared tools alongside the pack's own. The connection's initialize response states its exact scope, and is the authoritative answer for a given day.

This is deliberate, not multiplexing by accident. The meta-tools are what let a scoped connection answer a question this pack does not cover — via ask_pipeworx, which routes across the whole catalog — without you adding a second MCP server. There is currently no way to mount a pack endpoint without them; if the extra schemas cost you more context than the routing is worth, connect to the full gateway once rather than to several pack endpoints.

Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:

{
  "mcpServers": {
    "pipeworx": {
      "url": "https://gateway.pipeworx.io/mcp"
    }
  }
}

Both URLs reach the same gateway and the same 1865+ data sources. The only difference is which pack's tools are listed directly; ask_pipeworx reaches all of them from either one.

No MCP client? Call it over HTTP

This pack takes your own API key (_apiKey) — we don't front one for it, so there's no curl here that would run without it. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/forager_find_phone. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.

Run it from npm

@pipeworx/mcp-forager is a local stdio bridge to the Pipeworx gateway: your MCP client starts it with npx, and it forwards every call to the same https://gateway.pipeworx.io/forager/mcp endpoint shown above. It needs network access; there is no offline mode.

{
  "mcpServers": {
    "forager": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-forager"]
    }
  }
}

Without a key it calls anonymously, capped at 50 calls a day. A free account raises that to 200 a day: get a key at https://pipeworx.io/signup and add "env": { "PIPEWORX_API_KEY": "<your key>" } to the server entry. The key is sent as a Bearer token, the same way a hosted connection sends it, so calls are metered and billed exactly as they are there.

It lists only this pack's tools by default. Set PIPEWORX_META_TOOLS=1 to also list ask_pipeworx and the other gateway-wide tools.

Behind an HTTPS proxy: Node's built-in fetch does not read HTTPS_PROXY by default. Newer Node releases honour it when NODE_USE_ENV_PROXY=1 is set; check your Node version's documentation.

Using with ask_pipeworx

Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:

ask_pipeworx({ question: "your question about Forager data" })

The gateway picks the right tool and fills the arguments automatically.

More

• Docs and guides
• pipeworx.io

License

MIT