A guide for using USDA FoodData Central, a US government database of food and nutrient information. It explains how to match foods and preparations and how to interpret nutrient amounts and serving sizes.

Use it to compare foods, look up packaged products, and calculate nutrition for specified portions and preparations.

It prevents comparing the wrong food form, confusing product and nutrient identifiers, or treating search results as complete rankings. It also helps avoid mixing values per 100 grams with values per serving.

usda-guide — Skill for Claude Code by cyanheads/usda-mcp-server

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add cyanheads/usda-mcp-server --skill usda-guide

Clone the repo

git clone --depth 1 https://github.com/cyanheads/usda-mcp-server

Made for: Claude Code.

Or install usda-mcp-server, the plugin that ships this one along with the rest of its 35 skills, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/cyanheads/usda-mcp-server/usda-guide/github.svg)](https://agentmods.dev/skills/cyanheads/usda-mcp-server/usda-guide)

Your own site

<a href="https://agentmods.dev/skills/cyanheads/usda-mcp-server/usda-guide"><img src="https://agentmods.dev/badge/skills/cyanheads/usda-mcp-server/usda-guide/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/cyanheads/usda-mcp-server/usda-guide"><img src="https://agentmods.dev/badge/skills/cyanheads/usda-mcp-server/usda-guide.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 572 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00046	$0.00572
Opus 5.5	$0.00018	$0.00229
Sonnet 5.5	$0.00009	$0.00114
Haiku 4.5	$0.00005	$0.00057

Measured 12d ago against content hash 8ced29fb20a3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

usda-guide scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/usda-guide/SKILL.md · 33 lines

How it starts

The opening of the file, as written. The whole thing — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scope

Use USDA FoodData Central for a specified food's composition or a bounded comparison. It does not provide nutrient-ranked search: a few keyword matches cannot establish which foods have the most of a nutrient across the database.

Identifiers

Food fdcId, nutrient id, and legacy nutrient number identify different things. Use the nutrient id from usda_list_nutrients or a returned food profile for nutrient filtering; never substitute its legacy number or a food ID. If a nutrient filter unexpectedly returns nothing, inspect the unfiltered profile before concluding the nutrient is unavailable: related nutrient names can have distinct IDs.

Gates

Match the selected record's description to the requested preparation and edible form before using its values. Resolve a branded product by its description and available brand information rather than taking the first keyword match.
Check the nutrient basis before answering. Search values are per 100g even when the result also shows a product-label serving. A preview omitting a nutrient does not establish its absence; use usda_get_food for the full profile.
Inspect servingInfo before treating a serving as the user's household measure. The first defined portion is not automatically the requested cup, piece, or package. For another listed portion, use its gram weight explicitly. Do not infer a gram weight from a volume label without a known conversion.
Check missingData and failed before reporting a complete comparison or meal total. Missing values are unavailable, never zero; a nutrient row can be absent when no compared food reports it.
Keep comparison conclusions tied to the returned foods and common measurement basis. Equal-mass comparisons do not establish which food supplies more in the user's unequal portions.

Workflows

Comparable foods: Select records matching each requested preparation, then compare the requested nutrients on a common mass basis. Report missing coverage alongside the comparison.

Read the full file on GitHub · 33 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

12d ago First seen · 33 lines · 46 tokens per session scan A 8ced29fb20a3

Subscribe to this mod's changes

usda-guide is a skill published in the GitHub repository cyanheads/usda-mcp-server (1 stars, last pushed 13d ago), licensed Apache-2.0. It adds 46 tokens to every session and 572 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-27.

FDC Scientific bun food fooddata-central mcp mcp-server

usda-guide next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
usda-guidecyanheads/usda-mcp-server	Skill	1	13d ago	Apache-2.0	A	46	Claude Code
gbif-biodiversity-guidecyanheads/gbif-biodiversity-mcp-server	Skill	1	7d ago	Apache-2.0	A	81	Claude Code
skillasachs01/nutrition-mcp	Skill	0	9mo ago	MIT	A	0	Claude Code, Codex
imaging-data-commonssynthetic-sciences/openscience	Skill	4.4k	today	Apache-2.0	A	62	Claude Code, Codex
flow-cytometry-analysissynthetic-sciences/openscience	Skill	4.4k	today	Apache-2.0	A	67	Claude Code, Codex
datamolsynthetic-sciences/openscience	Skill	4.4k	today	Apache-2.0	A	67	Claude Code, Codex
genomic-intelligencesynthetic-sciences/openscience	Skill	4.4k	today	Apache-2.0	A	150	Claude Code, Codex