{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_v7kde2zm2abh","handle":"usda-mcp","url":"https://wellknown.network/agents/usda-mcp","links":{"self":"https://wellknown.network/agents/usda-mcp/record.json","html":"https://wellknown.network/agents/usda-mcp","markdown":"https://wellknown.network/agents/usda-mcp/record.md","api":"https://wellknown.network/api/v1/agents/usda-mcp","status":"https://wellknown.network/api/v1/agents/usda-mcp/status","claim":"https://wellknown.network/agents/usda-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/usda-mcp/claim.json","badge":"https://wellknown.network/agents/usda-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json"},"ard":{"identifier":"urn:air::server:usda-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"usda-mcp","summary":"MCP server exposing a USDA-accurate food database with deterministic macro math — no hallucinated nutrition numbers.","description":"# usda-mcp\n\n[![CI](https://github.com/Asquarer02/usda-mcp/actions/workflows/ci.yml/badge.svg)](https://github.com/Asquarer02/usda-mcp/actions/workflows/ci.yml)\n[![PyPI](https://img.shields.io/pypi/v/usda-mcp.svg)](https://pypi.org/project/usda-mcp/)\n[![Python](https://img.shields.io/pypi/pyversions/usda-mcp.svg)](https://pypi.org/project/usda-mcp/)\n[![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)\n\nAn [MCP](https://modelcontextprotocol.io) server that gives Claude a **USDA-accurate food\ndatabase and deterministic macro math** — so it looks nutrition numbers up instead of\nrecalling them, and calculates portions in Python instead of doing mental arithmetic.\n\nAsk *\"build me a high-protein vegan dinner at 40g protein, 30g carb, 15g fat\"* and you get\nan answer whose numbers are exactly right, because a linear solver produced them.\n\n```\nYou: high protein vegan dinner, 40g protein / 30g carb / 15g fat\n\nClaude: 147 g Beans (Dry) ....... 37.5g pro,    0g carb,  1.5g fat\n        5 oz Sweet Potato ......  2.5g pro,   30g carb,    0g fat\n        0.96 tbsp Olive Oil ....    0g pro,    0g carb, 13.5g fat\n        -----------------------------------------------------------\n        Total .................. 40.0g pro, 30.0g carb, 15.0g fat — 415 kcal\n```\n\n## Why this exists\n\nLLMs are unreliable at two things this domain depends on: recalling specific nutrition\nvalues, and arithmetic. Ask a model for the macros in 6 oz of chicken breast and you get a\nplausible number that is often wrong by 15–20%.\n\nThis server removes both failure modes. It contains **no AI logic at all** — no model\ncalls, no embeddings, no semantic search. It is a database and a pile of arithmetic. The\ncalling model does the reasoning (\"what counts as light?\", \"what goes with salmon?\") and\nthis server supplies every number.\n\n## Install\n\nRequires [uv](https://docs.astral.sh/uv/) (or any Python 3.10+ environment). Nothing else —\nno API key, no network access, no external services. It runs f…","publisher":{"name":"Ahmed","url":null},"homepage":"https://github.com/Asquarer02/usda-mcp","repository":"https://github.com/Asquarer02/usda-mcp/releases","version":"0.1.0","license":null,"protocols":["mcp"],"tags":["claude","macros","mcp","meal-planning","model-context-protocol","nutrition","usda"],"pricing":null,"endpoints":[{"url":"pypi:usda-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"knowledge.reasoning","name":"Reasoning & Planning","confidence":1,"provenance":"derived"},{"slug":"data.vector-search","name":"Vector Search","confidence":0.894,"provenance":"derived"}],"categories":["data","knowledge"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"usda-mcp","registry":"pypi","observedAt":"2026-09-10T15:25:01.614Z","publishedAt":"2026-07-31T14:39:36.762280Z","latestVersion":"0.1.0"}},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"usda-mcp","url":"https://pypi.org/project/usda-mcp/","firstSeenAt":"2026-09-10T15:22:58.606Z","fetchedAt":"2026-09-10T15:22:58.606Z","normalizedAt":"2026-09-10T15:22:58.606Z"}]},"firstSeenAt":"2026-09-10T15:22:58.606Z","updatedAt":"2026-09-10T15:25:01.614Z"}