Nass MCP Server

USDA NASS — Agricultural Statistics

The USDA National Agricultural Statistics Service. Crop production, livestock inventory, prices, planted/harvested acres, yields — the official US agricultural data. State and county level for major commodities. Free, no auth (light rate limit).

Part of Pipeworx — an MCP gateway connecting AI agents to 1476+ live data sources.

Why this matters for AI agents

For agricultural commodity questions — supply outlook, price trends, regional production — NASS is the authoritative source. Used by USDA's own analysts, commodity traders, and agribusiness. Pair with BLS for ag wages/PPI and Comtrade for global trade flows.

Common flows:

• Production estimates. "What's the corn production forecast?" → nass_query({commodity: "CORN", agg_level: "NATIONAL"}) → annual and monthly forecasts.
• State-level breakdown. Same query with state: "IOWA" for state-specific.
• Livestock inventory. "How many cattle in Texas?" → nass_query({commodity: "CATTLE", state: "TEXAS"}).
• Prices. Average farm-gate prices by commodity and time period.

Used by the agricultural_commodity_brief recipe.

Auth

NASS Quickstats requires a free API key from https://quickstats.nass.usda.gov/api. Pass via _apiKey. Without a key, calls fail; with one, generous limits.

Major commodities tracked

Field crops: corn, soybeans, wheat, cotton, rice, sorghum, barley, oats, peanuts, sugar.

Livestock: cattle (calves, steers, dairy), hogs, sheep, poultry (broilers, layers, turkeys).

Specialty: vegetables (potatoes, tomatoes), fruit (apples, citrus), tree nuts, ornamentals.

Use exact USDA commodity names — the API is finicky about spelling and capitalization.

Update cadence

The crop-progress reports are the highest-frequency signal.

Common pitfalls

• Year-over-year confusion in monthly reports. Mid-season Crop Production reports give a current-year forecast revised monthly. Compare to prior year, not to last month's forecast.
• Yield vs. production. Yield is per-acre (e.g., bushels/acre). Production is total (yield × harvested acres). They tell different stories.
• NASS isn't WASDE. The World Agricultural Supply and Demand Estimates (WASDE) is a separate USDA report that synthesizes NASS + global data with supply/demand forecasts. For "outlook" questions, you may want WASDE.
• State-level data sparser for minor crops. Detailed state-level coverage is best for top-producing states. Smaller producers may aggregate to "Other states" or have suppressed data.
• Imperial units. Bushels, pounds, head, acres. Comtrade uses kilograms — convert when cross-referencing.
• Reference period. Cattle reports are point-in-time (January 1 inventory); crop reports often cover marketing year (varies by crop). Read the metadata.

Quick Start

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

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

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/nass/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.

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 Nass data" })

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

More

• Docs and guides
• pipeworx.io

License

MIT