
Connects Claude to the USDA Foreign Agricultural Service API for querying global trade flows and agricultural production data. Part of the Pipeworx gateway ecosystem, which means you can either use this standalone FAS endpoint or tap into their full gateway covering 250+ data sources. The interesting bit is the ask_pipeworx pattern where you throw natural language questions at it and the gateway figures out which tool to call and how to structure the parameters. Useful when you're building agents that need authoritative data on crop production, export statistics, or commodity trade patterns without manually wiring up USDA's data formats.
FAS MCP — USDA Foreign Agricultural Service (trade & global production data)
Part of Pipeworx — an MCP gateway connecting AI agents to 1476+ live data sources.
| Tool | Description |
|---|---|
fas_exports | Check US agricultural exports by commodity and destination. Returns export volumes, values, and trade partner details. Use fas_commodity_codes to find commodity codes (e.g., "corn", "wheat"). |
fas_imports | Check US agricultural imports by commodity and origin country. Returns import volumes, values, and source country details. Use fas_commodity_codes to find commodity codes (e.g., "coffee", "cocoa"). |
fas_production | Get global agricultural production, consumption, and inventory data by commodity and country. Returns production volumes, supply estimates, consumption figures, and trade flows by year. |
fas_commodity_codes | Search agricultural commodity codes and names. Returns commodity IDs, descriptions, and categories. Use results with fas_production, fas_exports, and fas_imports. |
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"fas": {
"url": "https://gateway.pipeworx.io/fas/mcp"
}
}
}
tools/list at https://gateway.pipeworx.io/fas/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 1476+ data sources. The
only difference is which pack's tools are listed directly; ask_pipeworx
reaches all of them from either one.
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 Fas data" })
The gateway picks the right tool and fills the arguments automatically.
MIT