dev.anatome/anatome
dev.anatome/anatomeLog workouts and meals by telling your AI. 873 exercises, muscle diagrams, food lookup.
Tools · 36
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: …
Fetch one exercise by name, id, or random.
Resolve an exercise name into primary/secondary muscle layers for rendering.
List all 23 supported muscle slugs with anatomical names.
Render an SVG diagram of the human body with muscles highlighted in arbitrary colors. Returns SVG.
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.
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.
Schedule the signed-in user's routine into planned workouts from start_date. Coach assignment of another user is REST-only.
Search food products by name (Open Food Facts + USDA). Returns macros per 100g.
Lookup a food product by EAN/UPC barcode.
Log a workout with exercise sets (strength or cardio unified). Requires an app user context.
List the current app user's workouts (most recent first).
Log a meal (calories + macros + optional ingredients) for the current app user.
List the current app user's meals for a date range.
Log water intake (ml) for the current app user.
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 enable…
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 …
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 f…
Get the current app user's fitness profile (height, weight, macro + water goals, diet, active sports). Requires an app user context.
Log a cardio activity (run/bike/swim/etc.) for the current app user. Supports duration, distance, HR, power, calories.
List the current app user's cardio activities (most recent first).
Parse free-text meal description ('2 eggs and toast with butter') into structured items with grams + macros.
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).
Draft a meal plan. Not medical advice. confirm:true required. Pass health constraints so the draft can honour them.
Draft a workout plan. Not medical advice. confirm:true required. Pass health constraints so the draft can honour them.
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 rec…
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.
List the current app user's water intake entries for a date range. Requires X-App-User-Id.
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.
Delete a logged meal by id (soft delete, 30-day recovery window). Requires X-App-User-Id.
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 b…
Delete a logged workout and its sets by id (soft delete, 30-day recovery window).
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.
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; o…
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…
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 me…
Resources · 8
Renders a parsed meal as one row per food, marking which positions were matched to the food database and which the model estimated.
ui://widget/meal-breakdown
Renders the most recent day from a nutrition range as calorie and macro rings against the user's targets.
ui://widget/daily-nutrition
Renders per-muscle recovery percentages and highlights which muscles are fresh enough to train.
ui://widget/muscle-recovery
The complete REST contract — every path, parameter and response shape. Fetch this when a tool does not cover what you need; the REST surface is broader than the tool surface.
anatome://openapi
How to get a key, connect an MCP client, and make a first call. Start here.
anatome://llms.txt
Every tool with its complete input schema, in one document — so you need one read instead of parsing forty descriptions.
anatome://tools
The 23 muscle slugs accepted by generate_muscle_image and workout_image, with anatomical names. Use these exact strings — arbitrary muscle names are not resolved.
anatome://muscles
Which field names the write endpoints accept, which aliases are rewritten, and which look like aliases but are deliberately rejected because they would change units. Read before your first write.
anatome://write-policy
Prompts · 8
Record everything you ate, drank and trained today in one pass.
Pick today's session from your actual recovery state and recent training load.
An honest read on the last 7 days: training, nutrition, weight, adherence.
Build next week's training from a curated routine and your current load.
Bring meal history over from MyFitnessPal, Cronometer, Lose It! or MacroFactor.
Personal records, estimated 1RM trend, and whether the last block moved the needle.
Compare intake against targets, including the nutrients most trackers ignore.
Get a complete copy of everything anatome stores about you.
Similar MCP servers embedding-nearest
How to use
Add to your Claude Desktop / Cursor / Cline MCP config:
{
"mcpServers": {
"dev.anatome/anatome": {
"url": "https://anatome.dev/mcp",
"transport": "streamable-http"
}
}
}