Splyt
Server Details
Read-only access to your own Splyt training: workouts set by set, personal records, your training plan, habits and sleep. Splyt is a workout tracker for iPhone and Apple Watch. Sign in with your Splyt account over OAuth; nothing is ever written or changed.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- OAuth
- Works in Glama
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-06-18
- URL
- ChatGPT
- –
- Claude
- Splyt
TDQS
Scored across 9 tools
Training tools are reasonably distinct, but nutrition goal and calorie/macro targets appear in get_daily_health, get_nutrition, and get_training_overview, so an agent asking about targets must pick among three overlapping sources. get_exercise_progress vs get_personal_records also require careful reading (per-session progression vs period bests). Descriptions mitigate the overlap with explicit routing hints ('use this first', 'get_nutrition has the full food log'), but the boundaries are not clean.
Eight tools follow a get_<noun> pattern in consistent snake_case, and list_workouts is a deliberate, semantically correct use of list_ for a collection query (its id is then fed to get_workout). The single minor inconsistency is the get_/list_ mix and inconsistent noun style (get_habits vs get_daily_health vs list_workouts), but the pattern is highly predictable.
Nine tools is well-scoped for a fitness/nutrition assistant: each covers a distinct data domain (health metrics, workouts, exercise progression, PRs, plan, split snapshot, habits, nutrition). No tool feels like filler, and the count stays well within the comfortable 3-15 range.
Read coverage is broad across health, training, nutrition, habits, and personal records, with sensible linking (list_workouts -> get_workout). The obvious gap is that the surface is entirely read-only: an agent cannot log food/water, record a workout, complete a habit, or modify the training plan, which limits it to an advisory/query role.
Publisher details
- Operator
- Splyt · Publisher source
- Operator website
- https://splyt.fit · Publisher source
- Vendor relationship
- First-party
- Documentation
- https://splyt.fit/developers
- Privacy policy
- Not provided
- Trust center
- Not available
- Restrictions
- Requires a Splyt account (free; the app is on iPhone). Read-only. ChatGPT custom connectors need a paid ChatGPT plan; use https://splyt.fit/mcp/chatgpt there.
Available Tools
9 toolsget_daily_healthDaily healthBRead-onlyInspect
Day-by-day steps, sleep, active calories, body weight and water for a range of days, plus the user's nutrition goal and today's calorie/macro targets.
Inputs: days.
get_exercise_progressExercise progressARead-onlyInspect
How one lift has progressed: per session, the heaviest set, best estimated 1-rep max (Epley) and volume. Matches the exercise name loosely (e.g. "bench", "squat").
Inputs: exercise (required), weeks.
get_habitsHabitsBRead-onlyInspect
The user's active habits and how consistently they've completed each over a period.
Inputs: days.
get_nutritionNutritionARead-onlyInspect
The user's nutrition goal (lose fat / maintain / build muscle), their daily calorie and macro targets and how they were worked out, and what they've logged in Splyt's food log day by day — each entry as they typed it, with calories, protein, carbs and fat (AI estimates). Use it to answer what and how much they should eat for their goal.
Inputs: days.
get_personal_recordsPersonal recordsARead-onlyInspect
The user's best lifts over a period: heaviest weight and best estimated 1-rep max per exercise, with the date it happened.
Inputs: days, limit.
get_training_overviewTraining overviewARead-onlyInspect
A snapshot of the user right now: their active split, this week's workouts (done, missed and still planned), totals vs last week, today's plan, recent body weight, and their nutrition goal (lose fat / maintain / build muscle) with daily calorie and macro targets and what they've eaten today. Use this first — for training AND for any question about what or how much to eat. get_nutrition has the full food log.
Inputs: no named parameters.
get_training_planTraining planBRead-onlyInspect
What's planned: the active split and its days, and planned workouts for the coming days (with any missed days that were made up).
Inputs: days_ahead.
get_workoutWorkout detailsARead-onlyInspect
One workout in full: every exercise and its sets (weight × reps, or seconds for timed holds). Get session_id from list_workouts.
Inputs: session_id (required).
list_workoutsList workoutsARead-onlyInspect
Completed workouts in a date range, newest first, with name, duration and session id (for get_workout).
Inputs: days, limit.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Read-only access to your PumpX workout log: sessions, lift history, PRs, routines, measurements.
Read your workouts, history, and stats; create and schedule new workouts. Writes are additive only.
Your swim, bike and run training: readiness, HRV, sleep, workouts and race predictions. Read-only.
Read-only Apple Health data synced from your iPhone: sleep, heart rate, HRV, workouts and trends.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables read-only access to your WHOOP health data, including recovery, sleep, strain, workouts, cycles, and body measurements, through the official v2 API with OAuth 2.0.MIT
- AlicenseCqualityBmaintenanceEnables reading training history and planning complete workouts on a personal calendar, including exercises with videos, sets, reps, per-set weights, supersets, notes, and block instructions. It also supports searching the exercise library, copying or moving sessions, and retrieving performance stats, personal records, and feedback.29MIT
- AlicenseAqualityDmaintenanceProvides read-only access to Nolio training data including planned workouts, completed sessions, metrics, records, and notes.84MIT
- AlicenseNot gradedqualityCmaintenanceEnables read-only querying of an athlete’s workouts, training analysis, fitness load metrics, records, races, calendar, health metrics, equipment, strength sessions, and workout library through MCP clients, with no account modifications.MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.