Connect Anatome and your agent gets 36 tools, among them ai_meal_plan, ai_parse_meal, ai_photo_macros. It answers at https://anatome.dev/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 10 of 10 times since 5 September 2026; the last check, on 18 October 2026, succeeded.
Log workouts and meals by telling your AI. 873 exercises, muscle diagrams, food lookup.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
ai_meal_plan | Draft a meal plan. Not medical advice. confirm:true required. Pass health constraints so the draft can honour them. Inputs: days, goal, diet_type, daily_calories, confirm, health |
ai_parse_meal | Parse free-text meal description ('2 eggs and toast with butter') into structured items with grams + macros. Inputs: text, locale |
ai_photo_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). Inputs: image_url, image_base64 |
ai_workout_plan | Draft a workout plan. Not medical advice. confirm:true required. Pass health constraints so the draft can honour them. Inputs: days_per_week, goal, experience, confirm, health |
delete_meal | Delete a logged meal by id (soft delete, 30-day recovery window). Requires X-App-User-Id. Inputs: meal_id |
delete_workout | Delete a logged workout and its sets by id (soft delete, 30-day recovery window). Inputs: workout_id |
export_data | 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: domains, confirm |
generate_muscle_image | Render an SVG diagram of the human body with muscles highlighted in arbitrary colors. Returns SVG. Inputs: gender, view, layers |
get_body_metrics | 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: metric_type, from, to, limit |
get_cardio_activities | List the current app user's cardio activities (most recent first). Inputs: limit, date_from, date_to |
get_events | 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 g Inputs: since, entities, limit |
get_exercise | Fetch one exercise by name, id, or random. Inputs: name, id, random |
get_meals | List the current app user's meals for a date range. Inputs: date_from, date_to |
get_muscle_recovery | 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 |
get_nutrition_daily | 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_from, date_to |
get_profile | Get the current app user's fitness profile (height, weight, macro + water goals, diet, active sports). Requires an app user context. |
get_progress | 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 Inputs: metric, exercise, from, to, bucket, group_by |
get_routine | 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 |
get_water | List the current app user's water intake entries for a date range. Requires X-App-User-Id. Inputs: date, date_from, date_to |
get_workouts | List the current app user's workouts (most recent first). Inputs: limit, date_from, date_to |
instantiate_routine | Schedule the signed-in user's routine into planned workouts from start_date. Coach assignment of another user is REST-only. Inputs: idempotency_key, routine_id, start_date, cadence_days |
list_muscles | List all 23 supported muscle slugs with anatomical names. |
list_routines | 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: difficulty, goal, split_type, days_per_week, limit |
log_body_metric | 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: idempotency_key, date, metric_type, value, unit, notes |
log_cardio | Log a cardio activity (run/bike/swim/etc.) for the current app user. Supports duration, distance, HR, power, calories. Inputs: idempotency_key, date, sport, title, duration_seconds, distance_m |
log_meal | Log a meal (calories + macros + optional ingredients) for the current app user. Inputs: idempotency_key, date, meal_type, name, calories, protein |
log_water | Log water intake (ml) for the current app user. Inputs: idempotency_key, date, amount_ml |
log_workout | Log a workout with exercise sets (strength or cardio unified). Requires an app user context. Inputs: idempotency_key, date, title, primary_sport, sets |
lookup_barcode | Lookup a food product by EAN/UPC barcode. Inputs: barcode |
my_training_context | 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: workout_limit, domains |
resolve_exercise | Resolve an exercise name into primary/secondary muscle layers for rendering. Inputs: exercise |
search_exercises | 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, muscle, equipment, level, limit, cursor |
search_foods | Search food products by name (Open Food Facts + USDA). Returns macros per 100g. Inputs: q, locale, page_size |
update_meal | 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: idempotency_key, meal_id, date, meal_type, name, calories |
update_sets | 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_workou Inputs: set_ids, exercise, weight, reps, rpe, completed |
upsert_profile | 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 d Inputs: goal, height, weight, unit_system, language, timezone |
Every block below points at https://anatome.dev/mcp. Pick your client and copy.
claude mcp add --transport http anatome https://anatome.dev/mcp
{
"mcpServers": {
"anatome": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://anatome.dev/mcp"]
}
}
}{
"mcpServers": {
"anatome": {
"url": "https://anatome.dev/mcp"
}
}
}{
"servers": {
"anatome": {
"type": "http",
"url": "https://anatome.dev/mcp"
}
}
}{
"context_servers": {
"anatome": {
"url": "https://anatome.dev/mcp"
}
}
}{
"mcpServers": {
"anatome": {
"serverUrl": "https://anatome.dev/mcp"
}
}
}{
"mcpServers": {
"anatome": {
"url": "https://anatome.dev/mcp"
}
}
}name: Anatome
version: 0.0.1
schema: v1
mcpServers:
- name: Anatome
type: streamable-http
url: https://anatome.dev/mcp{
"mcpServers": {
"anatome": {
"httpUrl": "https://anatome.dev/mcp"
}
}
}{
"mcpServers": {
"anatome": {
"type": "http",
"url": "https://anatome.dev/mcp"
}
}
}{
"mcpServers": {
"anatome": {
"url": "https://anatome.dev/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fanatome.dev%2Fmcp&type=streamable_http&id=anatome&name=Anatome
It answered our last check on 18 October 2026 in 304 ms. Over 10 checks since 5 September 2026 it answered 10. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by anatome.dev and served from anatome.dev, the vendor's own domain: https://anatome.dev/mcp.
36, as returned by the server's own tools/list on 31 August 2026: ai_meal_plan, ai_parse_meal, ai_photo_macros, ai_workout_plan, delete_meal, delete_workout, export_data, generate_muscle_image, and 28 more.
It answered our last check on 18 October 2026 in 304 ms. Over 10 checks since 5 September 2026 it answered 10.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://anatome.dev/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: dev.anatome. Endpoint host: anatome.dev. ARD identifier: urn:air:dev.anatome:mcp:anatome.
First indexed 31 August 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.