metri: Calorie & Macro Tracker
Server Details
Track calories and macros right in Claude or ChatGPT and build a personal nutrition diary
- Status
- Healthy
- Uptime
- 50.0% over the last 24 hours
- OAuth
- Works in Glama
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 11 tools
Consumption operations are cleanly separated into log, edit, and delete, and food versus batch operations are clearly distinguished. The only mild overlap is among today-focused tools: metri_show_today, metri_today_details, and metri_get_diary all surface today's data, though their descriptions assign distinct card, app-fullscreen, and chat-diary roles.
All tools share the metri_ prefix and snake_case format, and most follow a predictable verb_noun pattern such as log_consumption, save_food, get_diary, and set_daily_goal. The main exception is metri_today_details, a noun phrase rather than a verb-led name, which slightly breaks the convention.
At 11 tools, the set is well-scoped for a tracker covering foods, batches, diary entries, goals, and dashboard views. Each tool appears to cover a distinct operation rather than padding the surface.
Core lifecycle coverage is strong: foods and batches can be created, updated, searched, deleted, and logged; diary entries can be logged, edited, retrieved, and deleted; goals and today views are present. No obvious dead ends appear for the calorie and macro tracking domain.
Publisher details
- Operator
- Polina Tolmacheva · Publisher source
- Operator website
- https://metri-diary.com
- Vendor relationship
- First-party
- Documentation
- https://metri-diary.com/support
- Privacy policy
- https://metri-diary.com/privacy
- Trust center
- Not available
- Restrictions
- Paid product with a free trial. Requires a metri account: users sign in with Google or an emailed code while connecting.
Available Tools
11 toolsmetri_delete_consumptionDelete food consumptionADestructiveIdempotentInspect
Delete an entire eating event and return the refreshed current-day dashboard. The operation is idempotent; use metri_edit_consumption to remove only one item.
Inputs: consumptionId (required). Returns: render, dashboard
metri_delete_foodDelete saved foodADestructiveIdempotentInspect
Delete a saved food or batch: it disappears from metri_search_foods and can no longer be logged. Diary entries and batches that already contain it keep its name and nutrition.
Inputs: foodId (required). Returns: name
metri_edit_consumptionEdit food consumptionADestructiveInspect
Correct a diary consumption using absolute target values. Returns the whole consumption as it now stands, shaped as in metri_get_diary, and the refreshed current-day dashboard. An item keeps its food as it was logged, so a quantity edit recalculates from that copy, not from later edits to the saved food; a batch item always reads its batch as last corrected.
Inputs: consumptionId (required), name, consumedAt, itemChanges. Returns: name, items, render, totals, +4 more
metri_get_diaryRead food diaryARead-onlyIdempotentInspect
Retrieve the user's diary for whole calendar days, newest entries first. Days are counted in the time zone metri keeps for the user's account, so pass the user's own dates: today, yesterday or this week become a first and a last day. The period may span at most 31 days; split longer periods into consecutive ones. Each entry's consumedAt is local time in that zone, with its UTC offset. Each entry lists its items; an item's grams is the logged amount (a batch item carries fractionOfBatch, plus grams when logged in grams), and serving is how the user counted it (for example 2 cups), so count servings from it rather than from grams. Totals are computed on the server over the whole period regardless of pagination, so use them instead of adding up entries. With query, only entries whose name or any item's food name contains the text are returned, each with all its items; totals then count every item of an entry whose name matches and, in other entries, only the items whose food name matches. Matching is a case-insensitive substring with no synonyms or translation: query each name the user may have logged a food under.
Inputs: to (required), from (required), query, cursor. Returns: totals, nextCursor, consumptions
metri_log_consumptionLog food consumptionAInspect
Record one complete eating event and return the refreshed current-day dashboard. Each item is a saved food by foodId or an inline non-batch food. Create a batch with metri_save_batch first, then log it by foodId. Log a batch by grams only when its finished weight is known; otherwise use fractionOfBatch. Returns each item's id and nutrition in the order of items.
Inputs: name (required), items (required), consumedAt. Returns: items, render, totals, warnings, +2 more
metri_save_batchSave batchADestructiveInspect
Save one batch: a single preparation the user actually cooked, for example a pot of soup or a tray of lasagna, not a reusable recipe. Without foodId, create a batch from name and components. With foodId, correct that batch: fields you omit keep their values, and every diary item of the batch follows the change. Cooking the dish again is a new batch, not a correction.
Each component is a saved non-batch food by foodId, or an inline food with name and nutritionPer100g. Components replace the whole list, so to change one, read the batch with metri_search_foods by foodId, edit the list and send all of it back.
outputWeightGrams is the finished weight of the whole batch. Pass null when it was not weighed; never estimate it. Without it, the batch can only be logged as a fraction. Changing it keeps the grams of items logged in grams and recomputes their fraction; items logged as a fraction keep their fraction. It cannot be cleared to null while items are logged in grams.
Inputs: name, foodId, components, outputWeightGrams. Returns: foodId, warnings, nutritionPer100g, totalBatchNutrition, +1 more
metri_save_foodSave foodADestructiveInspect
Create a reusable non-batch food, or update one by foodId: only the fields passed change. Does not log consumption.
Inputs: name, foodId, nutritionPer100g. Returns: name, foodId, warnings, nutritionPer100g
metri_search_foodsSearch saved foodsARead-onlyIdempotentInspect
Search the user's private metri library of saved foods and cooked batches. It reads only metri state, not the public web.
Pass at most one field:
foodId: read that one food in full; a batch includes its components.
query: search food names. Returns up to 20 matches in relevance order.
cursor: fetch the next 20 results of the previous search or browse.
nothing: browse the whole library, most recently changed first, 20 at a time.
Search and browse results omit batch components and include nextCursor when more results exist.
Search when the user refers to something personal or saved, such as their usual dish, a cooked batch or a specific product, and log with its foodId when it is the same food. Generic foods can be logged inline without a search.
Inputs: query, cursor, foodId. Returns: foods, nextCursor
metri_set_daily_goalSet daily nutrition goalAIdempotentInspect
Use this when the user wants to set or change their daily calorie target and optional protein, fat, or carbohydrate targets. Returns the previous goal and today's progress against the new goal, shown as a card. The new goal applies from now on, including the rest of today; days that have already ended keep the goal they were lived against. Nothing is deleted: earlier goals are kept, and the goal can be changed back at any time.
Inputs: kcal (required), fat, carbs, protein. Returns: render, dashboard, previousGoal
metri_show_todayShow today's nutrition progressARead-onlyIdempotentInspect
Use this when the user asks to see today's calories, macros, remaining daily allowance, or nutrition progress as a visual card.
Inputs: no named parameters. Returns: day, goal, render, totals
metri_today_detailsToday's full breakdownARead-onlyIdempotentInspect
App-only companion to metri_show_today: the full day grouped by eating event, with per-item macros and the batch component breakdown, used by the metri card's fullscreen view. day and summaryDays are dates as YYYY-MM-DD, counted in the account's time zone like the card's own day. Pass summaryDays to also get back the calorie and macro totals plus the goal in force for each of those days, which colour the day strip in that same view. Do not call this to answer the user in chat; use metri_get_diary instead.
Inputs: day (required), summaryDays. Returns: days, goal, items, meals, +2 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Calorie, workout and body-weight log inside ChatGPT and Claude. Log meals by text, photo or voice.
Calorie tracker app for ChatGPT and Claude: read meals, macros, weight and log meals from chat.
Log meals and read your nutrition diary from Claude or ChatGPT.
All the ease of Claude. All the rigor of a real macro tracker.
Related MCP Servers
- AlicenseAqualityAmaintenanceConnect MyFitnessPal to Claude or any MCP client. Log meals, search food database with macros, track trends, and export nutrition history against your real MyFitnessPal diary.18358 PyPI34MIT
- AlicenseNot gradedqualityCmaintenanceEnables logging meals, tracking calories and macros, reviewing daily and range summaries, setting weight goals, searching foods and recipes, and getting meal suggestions from any Claude client, with optional multi-user household support. Includes a local food database for items missing from FatSecret and OAuth-based authentication to FatSecret profiles.MIT
- AlicenseNot gradedqualityBmaintenanceEnables Claude to act as the memory and reasoning layer for nutrition tracking, letting users log meals from label photos or descriptions, save foods, recipes, meal-prep containers, and restaurant orders, record weigh-ins, and query targets, progress, and projections as tool calls. All writes are previewed with dry runs, checked for plausibility, and reversible.MIT
- AlicenseAqualityBmaintenanceEnables reading and writing your Cronometer food diary from Claude.ai and Claude Code, including food entries, notes, biometrics, exercises, and fasts.4117 npm2MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.