
Connects Claude to the USDA Food Data Central database through five straightforward tools: search foods by keyword, fetch full nutrient profiles by FDC ID, browse paginated food listings, pull food group categories, and grab just the nutrient values for a given food. Useful when you're building nutrition apps, analyzing recipes, or need authoritative data on macros and micronutrients for thousands of foods. Runs through the Pipeworx gateway, which means you can either hit this single source or connect to their full catalog of 673+ data sources. Includes an ask_pipeworx convenience method that takes natural language questions instead of structured tool calls.
USDA Food Data Central MCP — comprehensive nutrient database for US foods (~600k items across SR Legacy, Foundation, Survey, Branded, Experimental data types).
Part of Pipeworx — an MCP gateway connecting AI agents to 1476+ live data sources.
search_foods(query, data_type?, page_size?, page_number?, sort_by?, sort_order?, brand_owner?)get_food(fdc_id, format?, nutrients?) — single-food detaillist_foods(data_type?, page_size?, page_number?, sort_by?, sort_order?) — browselist_food_groups() — USDA food group referencenutrients_for_food(fdc_id, nutrient_numbers?) — convenience: just the nutrient valuesPLATFORM_USDA_FDC_KEY?_apiKey=<key> after registering at https://api.data.gov/signup/Free tier: 1000 req/hour.
https://api.nal.usda.gov/fdc/v1/ — api_key= query param.
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"usda-fdc": {
"url": "https://gateway.pipeworx.io/usda-fdc/mcp"
}
}
}
tools/list at https://gateway.pipeworx.io/usda-fdc/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 Usda Fdc data" })
The gateway picks the right tool and fills the arguments automatically.
MIT