Skip to main content
Glama
Nutrition MCP
by ronkommoji

Nutrition MCP

A filesystem-based MCP server that turns any MCP-capable AI agent into a conversational calorie and protein tracker: natural-language estimates, confidence-aware logging, daily/weekly progress, food-history search, and export. Works offline with local fallback data — no API keys required.

Quickstart

The server runs straight from GitHub via npx — no clone, no manual build (it self-builds on first fetch). You only need Node.js ≥ 20.

The one command every agent uses:

npx -y github:ronkommoji/nutrition-mcp

Pick your agent:

Agent

Guide

Hermes Agent

docs/install/hermes.md

Claude Code

docs/install/claude.md

Codex

docs/install/codex.md

Cursor / Windsurf / Claude Desktop / other

docs/install/generic-mcp.md

Claude Code users can install tools and the skill in one step:

/plugin marketplace add ronkommoji/nutrition-mcp
/plugin install nutrition-mcp

Related MCP server: Calorie Tracker MCP

What's included

  • MCP server — 8 tools + 2 resources (below).

  • Skill — skills/nutrition-tracking/SKILL.md: the estimate → confirm → log policy that makes the tools behave well. Auto-loaded by the Claude plugin; paste into system instructions / AGENTS.md for other agents.

Tools

  • setup_profile — create a user profile.

  • update_profile — update goals, weight, goal type, or timezone.

  • log_food — store a confirmed meal.

  • undo_last_log — remove the most recent entry.

  • get_daily_status — current day progress.

  • get_weekly_summary — weekly averages and tracked-day metrics.

  • search_food_history — search previous meals.

  • export_logs — export logs as JSON or CSV.

Resources

  • nutrition://user_profile

  • nutrition://daily_summary

Logging policy

The agent estimates calories and protein itself (its own knowledge plus web search), shows its assumptions, and logs only after the user confirms. log_food refuses any entry without userConfirmed: true.

Storage

Data is stored under ~/.nutrition-mcp/ by default (profile.json, logs/, weekly/, cache/, settings.json). Override with NUTRITION_MCP_HOME.

No API keys

There are none. The agent's own model estimates calories and protein (its knowledge plus web search), and the server only stores and reports them. The single optional setting is NUTRITION_MCP_HOME (storage location, default ~/.nutrition-mcp).

Local development

npm install
npm run build   # or: npm run dev   (tsx watch)
npm start

License

MIT

Available Tools

8 tools
export_logsC

Export profile and food logs as JSON or CSV text.

Inputs: format, endDate, startDate.

get_daily_statusA

Return calories, protein, remaining goals, and entries for a day.

Inputs: date.

get_weekly_summaryA

Return weekly calorie and protein averages, best day, and tracked-day count.

Inputs: date.

log_foodA

Store a confirmed food entry. The agent supplies calories and protein (estimated with its own knowledge or web search). Requires userConfirmed: true.

Inputs: protein (required), calories (required), rawEntry (required), userConfirmed (required), +4 more.

search_food_historyB

Search previous logged meals by raw text or parsed food item names.

Inputs: query (required), limit, endDate, startDate.

setup_profileB

Create the nutrition tracking profile used for daily goals and timezone-aware logging.

Inputs: weight (required), goalType (required), dailyCalorieGoal (required), dailyProteinGoal (required), +3 more.

undo_last_logA

Remove the most recent food log entry, optionally constrained to a specific date.

Inputs: date.

update_profileC

Update profile fields such as calorie goal, protein goal, weight, goal type, or timezone.

Inputs: name, weight, goalType, timezone, +3 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.5/5.0

    Scored across 8 tools

    Disambiguation4/5

    Most tools target clearly different actions and resources (logging, daily status, weekly summary, search, export, undo). The only mild overlap is setup_profile vs. update_profile, though the create-vs-modify distinction is spelled out in the descriptions.

    Naming Consistency5/5

    All eight names follow a consistent snake_case verb_noun pattern (setup_profile, log_food, get_daily_status, export_logs, etc.). Verb choices are predictable even though they vary by action.

    Tool Count5/5

    Eight tools is well within the ideal 3-15 range and each maps to a distinct part of the nutrition-tracking workflow. No tool feels redundant or missing for the core loop.

    Completeness4/5

    The surface covers profile setup/update, food logging, daily/weekly reads, history search, export, and single-step undo. Minor gaps exist: no way to edit or delete an arbitrary log entry (only undo the last), and no explicit get_profile read despite update/setup coverage.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      A Model Context Protocol (MCP) server that connects AI assistants to your MyFitnessPal data, enabling reading food diaries, nutrition goals, weight measurements, and more via MFP's web scraping.
      MIT
    • F
      license
      A
      quality
      D
      maintenance
      A local, JSON-first calorie and protein tracker for agents and shell workflows, providing a CLI and MCP server for meal tracking, goal management, and summaries with SQLite storage.
      11
      -
    • F
      license
      Not graded
      quality
      D
      maintenance
      Offline MCP server for logging workouts, tracking dietary macros, and retrieving daily summaries, all stored in local SQLite. Enables fitness tracking via natural language in MCP-compatible clients.
      -
    • A
      license
      Not graded
      quality
      D
      maintenance
      MCP server for personal nutrition tracking, enabling users to log meals with calories and macros, water intake, body weight, set goals, and import food diaries from other apps through natural language.
      MIT