Search foods, compare nutrients, and look up the full USDA FoodData Central database.
Search foods, compare nutrients, and look up the full USDA FoodData Central database. The usda mcp server wraps that behind the Model Context Protocol, so an assistant can use it through 7 defined tools rather than through you.
Everything the assistant can do here goes through one of these:
usda_search_foods — Search foods by keyword across SR Legacy, Foundation, Survey FNDDS, and Branded data sources, with nutrient preview and paginationusda_get_food — Full nutrient profile for one food by FDC ID, with optional per-portion scaling (g, oz, lb, kg, or serving)usda_get_foods — Batch nutrient fetch for 2–20 FDC IDs in a single request; failed IDs reported in failed[] instead of abortingusda_compare_foods — Side-by-side nutrient comparison for 2–5 foods, formatted as a markdown table scaled to a common gram basisusda_list_nutrients — Static FDC nutrient reference table (~150 nutrients) with IDs, names, units, and categories — no API call requiredPrerequisites — The Prerequisites tool exposed by this serverInstallation — The Installation tool exposed by this serverYou will need 3 environment variables: MCP_TRANSPORT_TYPE, MCP_LOG_LEVEL, USDA_FDC_API_KEY. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client. The configuration blocks on this page cover the common clients.
Among the file and storage access options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Usda's toolset — usda_search_foods, usda_get_food, usda_get_foods and 4 more — is a fair guide to whether it matches your workflow. It is maintained by cyanheads; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against Usda's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| usda_search_foods | Search foods by keyword across SR Legacy, Foundation, Survey FNDDS, and Branded data sources, with nutrient preview and pagination |
| usda_get_food | Full nutrient profile for one food by FDC ID, with optional per-portion scaling (g, oz, lb, kg, or serving) |
| usda_get_foods | Batch nutrient fetch for 2–20 FDC IDs in a single request; failed IDs reported in failed[] instead of aborting |
| usda_compare_foods | Side-by-side nutrient comparison for 2–5 foods, formatted as a markdown table scaled to a common gram basis |
| usda_list_nutrients | Static FDC nutrient reference table (~150 nutrients) with IDs, names, units, and categories — no API call required |
| Prerequisites | The Prerequisites tool exposed by this server. |
| Installation | The Installation tool exposed by this server. |
{
"mcpServers": {
"usda-mcp-server": {
"type": "stdio",
"command": "bunx",
"args": ["@cyanheads/usda-mcp-server@latest"],
"env": {
"MCP_TRANSPORT_TYPE": "stdio",
"MCP_LOG_LEVEL": "info",
"USDA_FDC_API_KEY": "your-api-key"
}
}
}
}Configuration as documented by the project. Restart the client after saving.
| Variable | Description | Required |
|---|---|---|
| MCP_TRANSPORT_TYPE | Configuration value read at startup. | Optional |
| MCP_LOG_LEVEL | Configuration value read at startup. | Optional |
| USDA_FDC_API_KEY | Credential the server authenticates with. | Yes |
Scoped local file access — read, write, search and reorganise files in directories you explicitly allow.
Search and read your Drive — Docs, Sheets and files become context your assistant can actually use.
Query, modify and analyse local SQLite databases in conversation — the fastest way to chat with a data file.
Build a programmable telecommunications stack for connecting telephony services with the Internet via a cloud-based utility.
Chat with your second brain — search, read and write vault notes through the Local REST API.
Connects AI models to an Obsidian knowledge base for direct access and manipulation of notes and folders.