@pipeworx/faostat

UN Food and Agriculture Organization statistics — crop and livestock production, food balance sheets, agricultural trade, land and input use, farm emissions, food security and producer prices, for 245 countries and territories since 1961.

Part of Pipeworx — an MCP gateway connecting AI agents to 1864+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

Tools

• faostat_domains(search?, domain_code?, limit?) — the 69 statistical domains, with last-updated date and observation count. Gives you the domain code.

• faostat_dimensions(domain_code, dimension, search?, limit?) — the valid area / element / item / year codes for a domain. Call this before the next one.

• faostat_data(domain_code, area?, element?, item?, year?, limit?) — the observations, with unit, year and data-quality flag.

Related MCP server: FAOSTAT MCP Server

Auth

Keyless.

Data sources

• https://bulks-faostat.fao.org/production/datasets_E.json — the domain catalogue. Carries DateUpdate and FileRows, which the query API does not.

• https://fenixservices.fao.org/faostat/api/v1/en/definitions/domain/{domain}/{dimension} — dimension code lists.

• https://fenixservices.fao.org/faostat/api/v1/en/data/{domain} — observations.

Things worth knowing:

• Two hosts, and they fail independently. fenixservices (the query API) was returning Cloudflare 521 on every path, then timing out, through 2026-09-17 22:00–23:00 UTC while this pack was built; bulks-faostat was unaffected throughout. The pack surfaces that as a named upstream outage — an empty array here would read as "this country grows nothing".

• faostatservices.fao.org is a different host and answers 401 Missing Authorization Header. It is not a drop-in substitute.

• bulks-faostat.fao.org serves the catalogue JSON but 403s on per-domain paths such as /production/QCL/QCL_AreaCodes_E.json; only the documented catalogue and the zip bulk files are readable.

• FAOSTAT codes are numeric and domain-specific. A wrong item code returns an empty result, not an error, which is why faostat_dimensions exists and why faostat_data says so explicitly on a zero-row answer.

• Not the codex-mrl pack — that also reads fao.org but serves Codex Alimentarius maximum residue limits.

Verified

2026-09-17 — faostat_domains returned all 69 domains with update dates and row counts. faostat_dimensions and faostat_data could not be verified: the FAO query host was down for the whole build window (see above).

Quick Start

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

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

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/faostat/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 1864+ 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

curl -X POST https://gateway.pipeworx.io/v1/tools/faostat_domains \
  -H 'Content-Type: application/json' \
  -d '{"search":"production"}'

No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/faostat_domains. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.

Run it from npm

@pipeworx/mcp-faostat 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/faostat/mcp endpoint shown above. It needs network access; there is no offline mode.

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

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 Faostat data" })

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

More

• Docs and guides

• pipeworx.io

License

MIT