anatome

Log workouts and meals by telling your AI.

CommunityOnlineNo sign-inGlobalFreeRead-only

What it can do

    What data it sees

    Do you need an account

    No: the server works without sign-in

    Log workouts and meals by telling your AI. 873 exercises, muscle diagrams, food lookup.

    How to connect

    How to connect anatome to Claude

    The server address to paste into Claude settings:

    https://anatome.dev/mcp

    1. Open Claude (claude.ai or the desktop app).
    2. Go to Settings → Connectors.
    3. Click Add custom connector.
    4. Paste the server address copied below into Remote MCP server URL and click Add.
    5. In a chat, click + → Connectors and switch the new connector on.

    Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

    Authorization

    After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

    How to connect anatome to ChatGPT

    The server address to paste into ChatGPT settings:

    https://anatome.dev/mcp

    1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
    2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
    3. Open Settings → Connectors and click Create.
    4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
    5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
    6. In a new chat open + → Apps/Connectors and enable the connector.

    OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

    Authorization

    On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

    How to connect anatome to Cursor

    The server address to paste into Cursor settings:

    https://anatome.dev/mcp

    Fastest: click Open in Cursor below and confirm the prompt.

    Manually:

    1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
    2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
    3. Save the file. The server appears in the MCP list; authorize it there if asked.

    Authorization

    If the service needs sign-in, an authorize button appears next to the server in the MCP list.

    Server tool list (36)

    Raw names from tools/list. Only developers need these.

    search_exercisesSearch 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`.
    get_exerciseFetch one exercise by name, id, or random.
    resolve_exerciseResolve an exercise name into primary/secondary muscle layers for rendering.
    list_musclesList all 23 supported muscle slugs with anatomical names.
    generate_muscle_imageRender an SVG diagram of the human body with muscles highlighted in arbitrary colors. Returns SVG.
    list_routinesBrowse the curated workout routine library (PPL, upper/lower, full-body, 5x5, etc.). Filter by difficulty, goal, split_type, days_per_week. Returns minimal list.
    get_routineFetch 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.
    instantiate_routineSchedule the signed-in user's routine into planned workouts from start_date. Coach assignment of another user is REST-only.
    search_foodsSearch food products by name (Open Food Facts + USDA). Returns macros per 100g.
    lookup_barcodeLookup a food product by EAN/UPC barcode.
    log_workoutLog a workout with exercise sets (strength or cardio unified). Requires an app user context.
    get_workoutsList the current app user's workouts (most recent first).
    log_mealLog a meal (calories + macros + optional ingredients) for the current app user.
    get_mealsList the current app user's meals for a date range.
    log_waterLog water intake (ml) for the current app user.
    log_body_metricLog 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.
    get_body_metricsList 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.
    upsert_profileUpsert 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.
    get_profileGet the current app user's fitness profile (height, weight, macro + water goals, diet, active sports). Requires an app user context.
    log_cardioLog a cardio activity (run/bike/swim/etc.) for the current app user. Supports duration, distance, HR, power, calories.
    get_cardio_activitiesList the current app user's cardio activities (most recent first).
    ai_parse_mealParse free-text meal description ('2 eggs and toast with butter') into structured items with grams + macros.
    ai_photo_macrosAnalyze 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).
    ai_meal_planDraft a meal plan. Not medical advice. confirm:true required. Pass health constraints so the draft can honour them.
    ai_workout_planDraft a workout plan. Not medical advice. confirm:true required. Pass health constraints so the draft can honour them.
    get_muscle_recoveryPer-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.
    get_nutrition_dailyPer-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.
    get_waterList the current app user's water intake entries for a date range. Requires X-App-User-Id.
    update_mealCorrect 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_mealDelete a logged meal by id (soft delete, 30-day recovery window). Requires X-App-User-Id.
    update_setsCorrect 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.
    delete_workoutDelete a logged workout and its sets by id (soft delete, 30-day recovery window).
    export_dataExport 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.
    get_eventsWhat 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.
    my_training_contextReturns 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.
    get_progressAny 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.