Skip to main content
Glama

fitness-mcp

A personal, remote MCP server for fitness data:

  • Garmin Connect activity data via garminconnect

  • Hevy workout data via the Hevy API

Designed to run on a Raspberry Pi behind nginx at something like:

https://mcp.home.owenrumney.co.uk/mcp

Tools

Garmin

  • list_garmin_activities

  • list_garmin_activities_by_date

  • get_garmin_last_activity

  • get_garmin_activity

  • get_garmin_activity_details

  • get_garmin_activity_splits

  • get_garmin_activity_weather

  • get_garmin_activity_types

Hevy

  • list_hevy_workouts

  • get_hevy_workout

  • list_hevy_routines

  • list_hevy_routine_folders

  • list_hevy_exercise_templates

Related MCP server: Hevy MCP

Local setup

Requires Python 3.12+.

uv sync
cp .env.example .env

Edit .env, then run the Garmin login helper once if your Garmin account needs MFA:

set -a
source .env
set +a
uv run fitness-mcp-garmin-login

Run the server locally over Streamable HTTP:

uv run fitness-mcp --transport streamable-http --host 0.0.0.0 --port 8000

Health check:

curl http://127.0.0.1:8000/health

MCP endpoint:

http://127.0.0.1:8000/mcp

If MCP_AUTH_TOKEN is set, callers must send:

Authorization: Bearer <MCP_AUTH_TOKEN>

Docker on Raspberry Pi

cp .env.example .env
mkdir -p data
# edit .env

docker compose build

docker compose run --rm fitness-mcp uv run fitness-mcp-garmin-login
docker compose up -d

The compose file publishes only to localhost:

127.0.0.1:8000 -> container:8000

Put nginx in front of it and proxy:

https://mcp.home.owenrumney.co.uk/mcp -> http://127.0.0.1:8000/mcp

See deploy/nginx.conf for an example site config.

Environment

MCP_AUTH_TOKEN=replace-with-a-long-random-value

GARMIN_EMAIL=you@example.com
GARMIN_PASSWORD=replace-me
GARMIN_TOKEN_STORE=/data/garmin

HEVY_API_KEY=replace-me
HEVY_BASE_URL=https://api.hevyapp.com/v1

Notes

  • Garmin Connect uses unofficial/private APIs through garminconnect, so MFA friction, rate limits, or upstream breakage are possible.

  • The server currently exposes read-only tools only.

  • If ChatGPT's MCP connector requires OAuth rather than bearer auth, this server will need an OAuth wrapper in front of the same /mcp backend.

Available Tools

13 tools
get_garmin_activityB

Get a Garmin Connect activity summary by activity ID.

Inputs: activity_id (required). Returns: object

get_garmin_activity_detailsB

Get detailed Garmin activity data, including charts and map polyline data.

Args: activity_id: Garmin activity ID. max_chart_points: Maximum chart samples Garmin should return. max_polyline_points: Maximum polyline points Garmin should return.

Inputs: activity_id (required), max_chart_points, max_polyline_points. Returns: object

get_garmin_activity_splitsC

Get split/lap data for a Garmin activity.

Inputs: activity_id (required). Returns: object

get_garmin_activity_typesB

List Garmin Connect activity type metadata.

Inputs: no named parameters. Returns: object

get_garmin_activity_weatherC

Get weather data associated with a Garmin activity.

Inputs: activity_id (required). Returns: object

get_garmin_last_activityA

Get the most recent Garmin Connect activity summary.

Inputs: no named parameters. Returns: result

get_hevy_workoutB

Get one logged Hevy workout by ID.

Inputs: workout_id (required). Returns: object

list_garmin_activitiesA

List recent Garmin Connect activities.

Args: start: Zero-based offset into the activity list. limit: Number of activities to return, capped at 100. activity_type: Optional Garmin activity type key, such as running, cycling, walking, swimming, hiking, strength_training, or cardio.

Inputs: start, limit, activity_type. Returns: result

list_garmin_activities_by_dateA

List Garmin Connect activities for a date range.

Args: start_date: Start date as YYYY-MM-DD. end_date: Optional end date as YYYY-MM-DD. If omitted, Garmin uses the start date only. activity_type: Optional Garmin activity type key. sort_order: Optional Garmin sort order, for example asc or desc.

Inputs: start_date (required), end_date, activity_type, sort_order. Returns: result

list_hevy_exercise_templatesC

List Hevy exercise templates.

Inputs: page, page_size. Returns: object

list_hevy_routine_foldersC

List Hevy routine folders.

Inputs: page, page_size. Returns: object

list_hevy_routinesC

List Hevy routines.

Inputs: page, page_size. Returns: object

list_hevy_workoutsA

List logged Hevy workouts.

Args: page: One-based page number. page_size: Number of workouts to return, capped at 100.

Inputs: page, page_size. Returns: object

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.4/5.0

    Scored across 13 tools

    Disambiguation5/5

    Tools are clearly separated by provider (Garmin vs. Hevy) and within each provider, each tool has a distinct purpose (listing, getting details, splits, weather, etc.). No overlapping functionality.

    Naming Consistency5/5

    All tools follow a consistent 'verb_provider_noun' pattern in snake_case. Verbs like list, get are used predictably. Only minor deviation is 'get_garmin_last_activity' which still fits the pattern.

    Tool Count5/5

    13 tools is well-scoped for a fitness server covering two platforms. It covers the essential read operations without being overwhelming or sparse.

    Completeness4/5

    The tool surface provides comprehensive read access for both Garmin and Hevy. Missing write operations (create/update/delete) are likely intentional given the server's focus on data retrieval. Minor gap: no tool to list Hevy routine folder contents or search across platforms.

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      C
      maintenance
      An MCP server that provides access to Garmin Connect fitness, health, and training data through 61 specialized tools. It enables users to query activities, sleep metrics, and performance stats directly within AI clients like Claude or Cursor.
      97
      238 npm
      191
      MIT
    • F
      license
      Not graded
      quality
      D
      maintenance
      An MCP server that connects AI clients to the Hevy workout tracking app, allowing users to manage routines and exercises. It enables reading workout history and logging new fitness sessions through simple natural language commands.
      -