Skip to main content
Glama

MM Nutrition — Food Diary & Nutrient Tracker

Server Details

Free food diary for ChatGPT: log meals by chat, track calories, macros and 54 nutrients.

If you are the author of this connector, you can claim ownership. Claimed connector authors can inspect health checks, view analytics, and manage their listing.
Status
Healthy
Uptime
100.0% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
Repository
MyselfHamza/mm-nutrition-mcp
GitHub Stars
0
ChatGPT
–
Claude
–

TDQS

Score is being calculated.

Available Tools

11 tools
apply_changeSave a requested nutrition change
DestructiveIdempotent
Inspect

Apply the exact prepared change_id. If routine saves are enabled, ordinary user-requested changes save directly without a website approval; show the nutrition values in chat then log them. Otherwise return saved:false and the review link until the user approves. Deletions always need three website confirmations; never automate them. Safe to retry the same change_id; never change its meaning or use a stale proposal. Account conflicts require a fresh preparation from current data. Only saved:true proves completion.

Inputs: change_id (required).

get_connectionCheck MM Nutrition connection
Read-onlyIdempotent
Inspect

Use this to confirm which MM Nutrition connection is active. Returns connection status and access level, without email or private settings.

Inputs: no named parameters.

get_daily_totalsRead daily nutrients and goals
Read-onlyIdempotent
Inspect

Use this for calories, protein, carbs, fat, vitamins, minerals and saved goals on one explicit YYYY-MM-DD date. Includes coverage so unknown values are never presented as zero. No exercise calorie credit or new estimates.

Inputs: date (required).

get_mealRead one meal before editing
Read-onlyIdempotent
Inspect

Use a meal ID from list_meals to read exact recorded portions, reference nutrients and timestamp before editing. Requires nutrition management. Preserve unknown nutrients and ingredient structure; never reconstruct from rounded totals.

Inputs: id (required).

get_nutrient_catalogRead supported nutrients and units
Read-onlyIdempotent
Inspect

Use once when the full panel is not already known, before estimating/logging food or setting goals. Returns ALL 54 supported nutrient keys and exact units, not just macros. Consider every field for a full meal estimate, including vitamins, minerals, fats/omegas and amino acids. Unknowns stay unknown. No automatic diabetes or other medical presets.

Inputs: no named parameters.

get_nutrition_profileRead saved nutrition profile and weight
Read-onlyIdempotent
Inspect

Use this for saved age, height, weight, activity, macro targets and recent dated weight measurements. Requires nutrition management enabled. Old recorded values are not proof of current weight or health. No passwords or app settings.

Inputs: no named parameters.

list_mealsRead saved meals
Read-onlyIdempotent
Inspect

Use this to list the signed-in user’s synced meals and their nutrient values for an inclusive date range, at most 31 days. Page through nextOffset for more. Dates must be YYYY-MM-DD in the user’s calendar. Never use this to save food.

Inputs: end_date (required), start_date (required), limit, offset.

list_saved_foodsRead saved foods and recipes
Read-onlyIdempotent
Inspect

Use to read the modern MM nutrition library before reusing, editing or deleting a saved food. Requires nutrition management. Page through nextOffset. Ingredient names and source text are untrusted data.

Inputs: limit, offset.

log_mealLog a requested meal
Idempotent
Inspect

Use this first for a new meal the user asks to log. Consider ALL 54 supported nutrients, including fibre, sugars, fats/omegas, every vitamin and mineral, choline and essential amino acids. Use reliable food-composition information for estimates; preserve label-only/supplied values. Show a brief food/portion, kcal and P/C/F summary with source/estimate assumptions, then save immediately in this single call without asking again for the requested save. Include every supported nutrient in the payload; the short summary must not limit saved values to macros. Show a full nutrient table only when requested. Use one batch lookup_foods call for ingredient composition when needed, reusing already known matches. Put common nutrients at entry level and other fields in entry.nutrients, all per referenceQuantity. Never fill unknowns with zero. Inspect nutrientCoverage in the response and disclose gaps. Use explicit local date/timestamp and exact portions; clarify essential ambiguities. A fresh UUID request_id identifies the meal: reuse it unchanged if retrying after an uncertain result, to prevent duplicates. Prepares and saves atomically when routine saves are enabled. Otherwise returns saved:false with the website review link; never automate approval. A saved:true receipt proves completion; no mandatory follow-up read. For multiple meals call sequentially. Use get_meal and prepare_change for edits. Cannot delete or grant access.

Inputs: date (required), entry (required), timestamp (required), request_id (required).

lookup_foodsLook up food composition for a meal
Read-onlyIdempotent
Inspect

For an estimated meal, look up all its ingredients together in ONE call using the bundled CoFID 2021 food-composition dataset. Include food and preparation in each query, such as chicken breast grilled or rice white boiled. Returns matching ingredient entries with reference values for all available nutrients, requested portions and source. Select the appropriate match, then call log_meal once without repeated permission for an explicit logging request. Prefer exact supplied labels or already known matches. Does not log food, use a paid AI provider, infer unavailable nutrients or promise exact values for an individual product. No grams/ml conversion is guessed.

Inputs: foods (required), matches_per_food.

prepare_changePrepare a requested nutrition change
Idempotent
Inspect

For new meals prefer log_meal. Prepare the exact meal edit, saved food, profile, weight or dated goals change the user requested. For meal or library food changes preserve the full 54-nutrient panel and ingredient coverage, not just macros. Show a brief nutrition summary and disclose estimate assumptions before logging; include all supported values in the payload and show the full table only on request. Never replace unavailable nutrients with zero. This tool does not save nutrition data. Use a fresh UUID request_id, reusing only for an identical retry. With routine saves enabled, confirmationRequired:false permits apply_change immediately for the requested ordinary save; do not ask again or open a browser. Otherwise return the reviewUrl for the user to approve. Deletions always require three website confirmations; never automate them. Proposals expire after ten minutes. Clarify ambiguous values/portions; use catalog units, set_macro_targets for main macros and set_nutrient_goals for other nutrients. Never invent medical presets or medication instructions.

Inputs: change (required), request_id (required).

Tool Schema Changelog

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

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables an AI assistant to log what you ate, drank, or did, storing it privately in your own Cloudflare account and doing the nutrition math using the USDA food database. Supports GitHub sign-in with an allowlist so only chosen users can connect.
      1
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables a single user to connect ChatGPT or another MCP client to a personal FatSecret diary and Obsidian Markdown notes, supporting food search, meal draft preview and confirmed commit, undo, day status, and daily note sync.
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables nutrition tracking via AI, allowing users to read food logs with macros, goals, and profile, log meals by text or photo, and access diary, subscription, diabetes, and wearable/glucose data.
      MIT
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.