Garmin Workouts MCP
The Garmin Workouts MCP server manages Garmin Connect workouts and activities, with enhanced support for strength training, payload inspection, and schema validation.
Workout Management
List, retrieve, delete, upload, and schedule workouts in Garmin Connect
Workout Authoring & Validation
Preview workout payloads before uploading (no credentials needed)
Validate workouts against the schema to catch mapping errors early
Retrieve the machine-readable JSON input schema for client integration
Generate workout data from a natural language description
Strength Training Support
List supported strength exercises with optional filtering
Resolve friendly aliases (e.g.
"t bar row") to Garmin internal enum mappingsHandles rep-based end conditions and flexible exercise definitions
Activity & Calendar Access
List, retrieve, and get weather data for Garmin Connect activities (with pagination, search, and type filtering)
View your Garmin Connect training calendar by year, month, or day
Flexible Authentication
Operates without Garmin credentials for non-Garmin tools (e.g., preview, schema inspection, exercise resolution)
Provides tools for managing Garmin Connect workouts, enabling users to create, preview, validate, list, and schedule strength and cardio workouts while resolving exercise metadata and supported sport types.
Garmin Workouts MCP
garmin-workouts-mcp is a standalone MCP server for Garmin Connect workouts.
It is intended as a focused extension for workflows that need a bit more structure around Garmin workout payloads, especially strength training.
This project is packaged as a stdio MCP server and can be published as an OCI image for MCP registries and Glama deployment. It is not a standalone public HTTP MCP endpoint.
Additions
Supports Garmin strength workout steps with
repsend conditions.Supports exercise metadata via explicit Garmin enums or friendly aliases.
Adds
preview_workout_payloadso payloads can be inspected before upload.Adds
validate_workoutfor early schema and mapping errors.Adds
resolve_supported_strength_exercisefor quick mapping checks.Adds
get_workout_input_schemafor machine-readable client integration.Includes
walkingas a supported sport type, which is also reflected in the prompt/schema.Keeps the familiar list/get/delete/schedule/calendar/activity tools.
Related MCP server: garmin-mcp
Environment
Garmin-backed tools authenticate lazily when they are called:
Authentication path:
GARMIN_EMAILandGARMIN_PASSWORD
The server can start without credentials. Tools that do not talk to Garmin, such as payload preview and schema inspection, still work without secrets.
Workout Input
The upload and preview tools accept a JSON object shaped like this:
{
"name": "Upper Day",
"type": "strength",
"steps": [
{
"stepType": "warmup",
"endConditionType": "lap.button",
"stepDescription": "General warm-up"
},
{
"stepType": "interval",
"exercise": "incline db press",
"endConditionType": "reps",
"stepReps": 8,
"stepDescription": "8-10 reps"
},
{
"stepType": "rest",
"endConditionType": "time",
"stepDuration": 120
}
]
}For strength exercises, either pass a friendly alias:
{ "exercise": "t bar row" }or explicit Garmin enums:
{
"exercise": {
"category": "ROW",
"exerciseName": "T_BAR_ROW"
}
}You can also inspect the accepted structure programmatically through get_workout_input_schema, or resolve likely Garmin strength mappings with resolve_supported_strength_exercise.
Development
Run tests in Docker Compose:
docker compose run --rm testsBuild the runtime image:
docker build -t garmin-workouts-mcp:local .Smoke test the stdio server startup without Garmin credentials:
python - <<'PY'
import subprocess
proc = subprocess.Popen(
["bash", "-lc", "tail -f /dev/null | docker run --rm -i garmin-workouts-mcp:local"]
)
try:
proc.wait(timeout=5)
print(f"container exited early with code {proc.returncode}")
finally:
if proc.poll() is None:
proc.terminate()
proc.wait()
print("container stayed up for 5 seconds")
PYPublishing
The intended OCI image location is:
ghcr.io/pranciskus/garmin-workouts-mcpRegistry metadata lives in server.json. The OCI image carries the required label:
io.modelcontextprotocol.server.name=io.github.pranciskus/garmin-workouts-mcpGlama ownership metadata lives in glama.json. It declares the GitHub maintainer account that can claim and manage the Glama listing.
Available Tools
15 toolsdelete_workoutD
Inputs: workout_id (required). Returns: result
generate_workout_data_promptD
Inputs: description (required). Returns: object
get_activityD
Inputs: activity_id (required). Returns: object
get_activity_weatherD
Inputs: activity_id (required). Returns: object
get_calendarD
Inputs: year (required), month (required), day, start. Returns: object
get_workoutD
Inputs: workout_id (required). Returns: object
get_workout_input_schemaD
Inputs: no named parameters. Returns: object
list_activitiesD
Inputs: limit, start, activityType, search. Returns: object
list_supported_strength_exercisesD
Inputs: query. Returns: object
list_workoutsD
Inputs: no named parameters. Returns: object
preview_workout_payloadD
Inputs: workout_data (required). Returns: object
resolve_supported_strength_exerciseD
Inputs: query (required). Returns: object
schedule_workoutD
Inputs: workout_id (required), date (required). Returns: object
upload_workoutD
Inputs: workout_data (required). Returns: object
validate_workoutD
Inputs: workout_data (required). Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 15 tools
Most tools target distinct actions (list, get, delete, upload, validate) but there is some overlap in workout-related operations like generate_workout_data_prompt, preview_workout_payload, and get_workout_input_schema which may confuse an agent. Also, list_workouts and list_activities are distinct but could be ambiguous without descriptions.
The majority of tools follow a consistent verb_noun pattern (list_workouts, delete_workout, validate_workout, get_activity). However, 'resolve_supported_strength_exercise' and 'generate_workout_data_prompt' deviate slightly from the simpler pattern of other tools, introducing minor inconsistency.
Fifteen tools is within a reasonable range for a workout management server, covering CRUD, validation, preview, and activity retrieval. The count feels slightly heavy but each tool seems to serve a purpose, and it is not excessive for the apparent feature set.
The server covers core workout lifecycle operations (list, get, upload, delete) plus validation, preview, and schema retrieval. Missing update functionality for workouts is a notable gap, but the domain appears covered for typical workout management workflows.
Maintenance
Related MCP Connectors
MCP server for Withings health data — sleep, activity, heart, and body metrics.
List, fetch, create, edit (replace), delete and schedule structured workouts on Garmin Connect (runn
Unofficial Wger MCP — wraps wger Workout Manager REST API (free, no auth for read)
Adaptive running coach MCP server — training data, plans, and recovery for AI assistants.
Related MCP Servers
- AlicenseNot gradedqualityAmaintenanceAn MCP server featuring an interactive React UI for Garmin Connect integration. It allows users to access and interact with Garmin fitness and health data through the Model Context Protocol.371 npm17MIT
- AlicenseNot gradedqualityCmaintenancePersonal MCP server for interacting with your Garmin Connect data. Exposes 62 tools across 11 domains including activities, health, training, and workouts.1MIT
- AlicenseAqualityDmaintenanceMCP server that exposes Garmin Connect health and activity data (steps, sleep, stress, activities, etc.) via tools for querying, analysis, and visualization.17Apache 2.0
- AlicenseBqualityCmaintenanceExposes personal Garmin Connect data to MCP-capable clients like Claude and Gemini. Enables querying daily stats, heart rate, sleep, activities, and managing workouts.16MIT