usda-mcp-server

Look up the FDC nutrient reference table — all tracked nutrients with their numeric IDs, names, SR reference numbers, units, and categories. Use to resolve a nutrient name (e.g. "vitamin C") to its FDC ID (1162) before passing it to the nutrients[] filter on other tools. Filter by category (macronutrients, vitamins, minerals, lipids, amino_acids, or other) to narrow results. The data is static — call once and reuse the IDs.

Search USDA FoodData Central foods by keyword. Returns matching foods with FDC IDs and a preview of key nutrients (energy, protein, fat, carbs — not guaranteed complete). Use the returned fdcId with usda_get_food for the full nutrient profile, or usda_compare_foods for side-by-side comparisons. When dataType is omitted, defaults to SR Legacy (common whole foods with complete profiles) — or to Branded when brandOwner is set, since only Branded records carry one. Set dataType to ["Branded"] for packaged products, or include a UPC/GTIN code as the query. Pass brandOwner (e.g. "General Mills") to narrow branded results.

Get the full nutrient profile for one food by FDC ID. Returns all available nutrients (or a filtered subset via the nutrients[] param) with optional per-portion scaling. Use usda_search_foods to discover FDC IDs. Provide quantity + unit to scale all nutrient values from per-100g to the specified portion (e.g. quantity=200, unit="g" → per-200g values). Use unit="serving" to scale to the food's first defined portion weight. Narrow nutrients[] to specific IDs to reduce response size for focused queries.

Fetch nutrient profiles for 2–20 foods in a single API call. More efficient than calling usda_get_food N times when you already have multiple FDC IDs. All values are per 100g (no portion scaling). Use the nutrients[] filter to limit response size — strongly recommended for batch calls. For side-by-side comparison with a formatted table, use usda_compare_foods instead. Failed IDs (not found or no data) are reported in the failed[] array rather than aborting the entire batch.

Compare nutrients side-by-side for 2–5 foods. Returns a structured table — one row per nutrient, one column per food — formatted as markdown. Best for "spinach vs kale iron" or "which has more protein?" questions. Omit nutrients[] to use the 12 most common defaults (energy, protein, fat, saturated fat, carbs, fiber, sugars, sodium, potassium, calcium, iron, vitamin C); provide nutrients[] with specific FDC IDs to compare different nutrients. All values are scaled to the same gram basis (default 100g). If one or more FDC IDs are not found, the comparison proceeds with the valid foods — only throws too_few_foods when fewer than 2 IDs return data.