anatome
Server Details
Log workouts and meals by telling your AI. 873 exercises, muscle diagrams, food lookup.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-06-18
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 36 tools
Most tools target distinct resources, but there are overlapping paths: get_progress with metric=muscle_recovery duplicates get_muscle_recovery, log_workout claims cardio support alongside log_cardio, and get_exercise/search_exercises/resolve_exercise are adjacent exercise lookups. Descriptions help clarify intent, but an agent could still select the wrong tool in several cases.
Verb_noun naming dominates, but read operations are split inconsistently between get_ and list_ (get_meals vs list_routines), AI tools use a separate ai_ prefix, and my_training_context is a bare noun phrase rather than a verb-led action. The patterns are readable but not predictable enough for a highly coherent set.
At 36 tools, the surface exceeds the 25+ threshold and feels sprawling for an agent to navigate. Several tools could be consolidated, such as the AI meal parsing/photo analysis pair or the overlapping progress/recovery tools, without losing functional coverage.
Core lifecycle coverage is strong: meals and workouts support log/read/update/delete, foods support search/lookup, routines support browse/fetch/instantiate, and profile/body metrics/water/cardio have read and write paths. Minor gaps exist, such as no delete/update for cardio, water, or body metrics, but these are easily worked around.
Available Tools
36 toolsai_meal_planAInspect
Draft a meal plan. Not medical advice. confirm:true required. Pass health constraints so the draft can honour them.
Inputs: days (required), confirm (required), goal, health, +2 more.
ai_parse_mealAInspect
Parse free-text meal description ('2 eggs and toast with butter') into structured items with grams + macros.
Inputs: text (required), locale.
ai_photo_macrosAInspect
Analyze a meal image and estimate foods + macros. Pass exactly one of image_url or image_base64. Vision model, capped separately from the text AI budget (free tier 1/mo).
Inputs: image_url, image_base64.
ai_workout_planAInspect
Draft a workout plan. Not medical advice. confirm:true required. Pass health constraints so the draft can honour them.
Inputs: confirm (required), days_per_week (required), goal, health, +1 more.
delete_mealADestructiveInspect
Delete a logged meal by id (soft delete, 30-day recovery window). Requires X-App-User-Id.
Inputs: meal_id (required). Returns: deleted
delete_workoutADestructiveInspect
Delete a logged workout and its sets by id (soft delete, 30-day recovery window).
Inputs: workout_id (required). Returns: deleted
export_dataARead-onlyIdempotentInspect
Export the signed-in user's data as JSON. Pass domains (e.g. meals,workouts) or confirm:true for a full copy. Identity comes from the token, never a caller-supplied user id.
Inputs: confirm, domains.
generate_muscle_imageBInspect
Render an SVG diagram of the human body with muscles highlighted in arbitrary colors. Returns SVG.
Inputs: layers (required), view, gender. Returns: svg, format, muscles_rendered
get_body_metricsARead-onlyIdempotentInspect
List the current app user's body metrics / measurements (weight, height, bicep, body fat, etc.), most recent first. Filter by metric_type (e.g. 'weight', 'bicep') and/or a date range. Requires an app user context.
Inputs: to, from, limit, metric_type. Returns: items
get_cardio_activitiesBRead-onlyIdempotentInspect
List the current app user's cardio activities (most recent first).
Inputs: limit, date_to, date_from. Returns: items
get_eventsARead-onlyIdempotentInspect
What changed since a cursor, including DELETES, which a list read cannot show. Returns {seq, entity, id, action}. Pass the last seq back as since on the next call to receive only entries after it; omit since for a first sync. seq is a global counter: gaps in your feed are other accounts' events, not lost data. Judge completeness from has_more, not seq.
Inputs: limit, since, entities.
get_exerciseARead-onlyIdempotentInspect
Fetch one exercise by name, id, or random.
Inputs: id, name, random.
get_mealsARead-onlyIdempotentInspect
List the current app user's meals for a date range.
Inputs: date_to, date_from. Returns: items
get_muscle_recoveryARead-onlyIdempotentInspect
Per-muscle 7-day recovery % (Fitbod parity) — the 'what should I train today?' input. Recommends fresh muscles. Pass include_bodyweight=true to add the user's bodyweight to bodyweight exercises so recovery reflects real load.
Inputs: include_bodyweight. Returns: muscles, window_days, threshold_volume
get_nutrition_dailyARead-onlyIdempotentInspect
Per-day calories, macros, fiber/sugar/sodium/alcohol, water, targets and adherence % over a date range (default: last 7 days). The 'how am I tracking today?' tool. Requires X-App-User-Id.
Inputs: date_to, date_from. Returns: to, days, from, limits, +1 more
get_profileARead-onlyIdempotentInspect
Get the current app user's fitness profile (height, weight, macro + water goals, diet, active sports). Requires an app user context.
Inputs: no named parameters.
get_progressARead-onlyIdempotentInspect
Any progression metric for the current user — pick one in metric. training_load is acute:chronic (>1.5 ramping too fast, <0.8 detraining); muscle_recovery is per-muscle freshness; correlate takes metric_a vs metric_b. Only completed sets count.
Inputs: metric (required), to, days, from, +10 more.
get_routineARead-onlyIdempotentInspect
Fetch a single curated routine by slug with all days + slots fully expanded (exercises, sets, reps ranges, rest, superset groupings). The 'give me a full program' tool.
Inputs: slug (required).
get_waterARead-onlyIdempotentInspect
List the current app user's water intake entries for a date range. Requires X-App-User-Id.
Inputs: date, date_to, date_from.
get_workoutsARead-onlyIdempotentInspect
List the current app user's workouts (most recent first).
Inputs: limit, date_to, date_from. Returns: items
instantiate_routineAInspect
Schedule the signed-in user's routine into planned workouts from start_date. Coach assignment of another user is REST-only.
Inputs: routine_id (required), start_date (required), cadence_days, idempotency_key.
list_musclesARead-onlyIdempotentInspect
List all 23 supported muscle slugs with anatomical names.
Inputs: no named parameters.
list_routinesARead-onlyIdempotentInspect
Browse the curated workout routine library (PPL, upper/lower, full-body, 5x5, etc.). Filter by difficulty, goal, split_type, days_per_week. Returns minimal list.
Inputs: goal, limit, difficulty, split_type, +1 more.
log_body_metricAInspect
Log a body measurement. metric_type: weight (kg), height (cm), body_fat (%), muscle_mass (kg), waist/chest/bicep/forearm/hip/thigh/calf/neck/shoulder (cm), bmi, resting_hr (bpm). Logging weight enables bodyweight-inclusive volume analytics.
Inputs: date (required), unit (required), value (required), metric_type (required), +2 more. Returns: id, date, value, metric_type
log_cardioBInspect
Log a cardio activity (run/bike/swim/etc.) for the current app user. Supports duration, distance, HR, power, calories.
Inputs: date (required), sport (required), notes, title, +5 more. Returns: id, date, sport, distance_m, +1 more
log_mealBInspect
Log a meal (calories + macros + optional ingredients) for the current app user.
Inputs: date (required), name (required), calories (required), fats, +4 more. Returns: id, date, fats, name, +3 more
log_waterAInspect
Log water intake (ml) for the current app user.
Inputs: date (required), amount_ml (required), idempotency_key. Returns: id, ml, date
log_workoutAInspect
Log a workout with exercise sets (strength or cardio unified). Requires an app user context.
Inputs: date (required), sets, title, primary_sport, +1 more. Returns: id, date, title
lookup_barcodeARead-onlyIdempotentInspect
Lookup a food product by EAN/UPC barcode.
Inputs: barcode (required). Returns: found, barcode, message
my_training_contextARead-onlyIdempotentInspect
Returns a slice of the signed-in user's training picture. Default domains are workouts and today's nutrition. Pass domains to add checkin, notes or profile, or domains=all. Identity comes from the token, not a caller-supplied user id.
Inputs: domains, workout_limit. Returns: date, domains, profile, recent_notes, +3 more
resolve_exerciseARead-onlyIdempotentInspect
Resolve an exercise name into primary/secondary muscle layers for rendering.
Inputs: exercise (required).
search_exercisesARead-onlyIdempotentInspect
Search 873 exercises by name with muscle/equipment/level filters. Rows are lean (name, ext_id, equipment, level, muscles) — enough to pick one; get_exercise returns instructions and media. Paginates: pass next_cursor back as cursor.
Inputs: q (required), level, limit, cursor, +3 more. Returns: results, next_cursor, total_matched
search_foodsARead-onlyIdempotentInspect
Search food products by name (Open Food Facts + USDA). Returns macros per 100g.
Inputs: q (required), locale, page_size. Returns: count, items
update_mealAInspect
Correct a previously logged meal — name, macros, nutrients, portion, date or meal_type. Pass only the fields you want to change. Requires X-App-User-Id.
Inputs: meal_id (required), date, fats, name, +10 more. Returns: id, date, fats, name, +3 more
update_setsADestructiveInspect
Correct sets already logged, by set id (log_workout returns them). Relabel the exercise, fix weight/reps/rpe, mark completed, add notes, or delete. Selection and change are separate, so a subset can be relabelled. Adding a set is log_workout, not this.
Inputs: set_ids (required), rpe, reps, notes, +4 more. Returns: deleted, missing, updated
upsert_profileAIdempotentInspect
Upsert the current app user's fitness profile. Set timezone first: every daily total, streak and adherence window is bucketed by it and defaults to UTC. weight doubles as the fallback bodyweight for bodyweight-inclusive volume when no dated weight metric exists.
Inputs: goal, height, weight, language, +13 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Workout log your AI fills in: sets from text or notebook photos, daily plans, history and records.
The workout tracker your AI can edit: build programs, swap exercises and read your logged sets.
Bring-your-own-AI fitness coach: your AI logs and reads your food, lifting, runs, sleep and weight.
Calorie, workout and body-weight log inside ChatGPT and Claude. Log meals by text, photo or voice.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceA comprehensive AI-powered fitness tracking application that enables AI tools to interact intelligently with user fitness data, providing personalized workout plans, nutrition tracking, and progress analysis through natural language.15MIT
- AlicenseNot gradedqualityBmaintenanceEnables conversational logging and retrieval of workouts, sets, weigh-ins, meals, goals, plans, and progress photos through MCP-capable AI clients, with authenticated per-user storage and export/query capabilities.ISC
- AlicenseAqualityFmaintenanceLets users log workouts and meals conversationally, with nutrition data, streak tracking, and generated shareable cards.1514 PyPI1MIT
- AlicenseNot gradedqualityBmaintenanceSelf-hosted fitness tracking MCP server that gives AI assistants access to your nutrition, training, weight, sleep, and accomplishment data via 77 tools and 5 resources. Enables natural-language logging and querying of personal health metrics through Claude or ChatGPT.1BSD 2-Clause "Simplified"
Glama MCP Gateway
Add one secure layer between your agents and this server.