Skip to main content
Glama
Sports Tracker MCP Server

Sports Tracker MCP Server

by wilkar

Sports Tracker MCP Server (Unofficial)

License: MIT Python 3.11+ FastMCP Code style: black Type Checked: mypy

Ask your AI assistant about your training: workouts, VO2Max trends, training load, recovery, and lifetime stats β€” answered with interactive cards.

IMPORTANT

Unofficial Project: This project is an independent, open-source Model Context Protocol (MCP) server. It is not affiliated with, endorsed by, sponsored by, or associated with Sports Tracking Technologies Ltd, Amer Sports, Suunto, or any of their affiliates or subsidiaries. All registered trademarks, product names, and company logos are the property of their respective owners.

NOTE

Runs locally, always. The server talks to Sports Tracker with a session key taken from your own browser. That key is tied to your account and never leaves your machine β€” so there is no hosted version of this server, and there cannot be one.


πŸš€ Quick start

1. Get your session key

Log in to Sports Tracker Web, open DevTools (F12 / Cmd+Option+I) β†’ Network, refresh the page, click any request to api.sports-tracker.com, and copy the value of the STTAuthorization request header.

WARNING

Treat this key like a password β€” it grants full access to your Sports Tracker account. Never paste it into an issue, a gist, or a shared config. It alsoexpires: when tools start failing with an authentication error, repeat this step to get a fresh one.

2. Add the server

Claude Code β€” one command:

claude mcp add sports-tracker -e STT_SESSION_KEY=your_session_key_here \
  -- uvx --from git+https://github.com/wilkar/sports-tracker-mcp sport-tracker-mcp

Claude Desktop β€” add to claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/claude_desktop_config.json, Windows: %APPDATA%\Claude\claude_desktop_config.json):

{
  "mcpServers": {
    "sports-tracker": {
      "command": "uvx",
      "args": ["--from", "/path/to/the/repo", "sport-tracker-mcp"],
      "env": {
        "STT_SESSION_KEY": "your_session_key_here"
      }
    }
  }
}

Cursor / Antigravity β€” add the same JSON block to your MCP settings (mcp_config.json).

Nothing to clone and no virtualenv to manage: uv fetches and runs the server on demand. If your client reports uvx: command not found, use the absolute path from which uvx (e.g. /opt/homebrew/bin/uvx).

3. Ask it something

"How far did I run in the last 7 days?"

That's it. If you get an answer, you're done.


Related MCP server: GC-MCP

πŸ› οΈ Available MCP Tools

Tool

UI Card

Description

Parameters

get_recent_workouts

βœ…

Fetch recent workouts with interactive sport and limit filters, clickable workout rows, and metrics.

limit (default: 10, supports 5, 10, 25, 'all'), imperial (default: false), sport (optional)

get_workout_details

βœ…

In-depth workout analysis with interactive time series charts (HR, altitude, speed), HR zones, ascent/descent, and Suunto extensions.

workout_key (required), imperial (default: false)

get_training_load_and_recovery

βœ…

Recovery gauge, cumulative recovery hours, TSS, PTE, and EPOC metrics.

None

get_training_summary

βœ…

Aggregated volume, distance, time, and calories across sports for the past N days.

days (default: 7), imperial (default: false)

get_vo2_max_history

βœ…

Aerobic capacity (VO2Max) trendline and fitness age progression extracted from workouts.

limit (default: 20)

get_user_stats

βœ…

Lifetime aggregate statistics and per-sport totals (distance, duration, calories, count).

username (optional), imperial (default: false)

get_recent_activities_summary

βœ…

Breakdown of sport frequency, total duration, and last performed dates over the past N days with interval selector.

days (default: 14)

get_social_feed

❌ (data-only)

Retrieve feed items from followed athletes or community members.

limit (default: 10), imperial (default: false)

Cards render as interactive HTML in hosts that support MCP Apps (io.modelcontextprotocol/ui); every tool also returns plain structured data, so clients without UI support lose nothing.

More things to ask

  • "How much running and cycling have I logged over the past 14 days? Break it down by distance, time, and pace."

  • "Give me a detailed breakdown of my latest workout, including heart rate zones, elevation gain, and Suunto metrics in imperial units."

  • "What is my current recovery time, TSS, and EPOC? Am I ready for a tempo run today?"

  • "Plot my VO2Max and fitness age progression over my last 20 workouts."


βš™οΈ Configuration reference

Variable

Required

Default

Description

STT_SESSION_KEY

Yes

β€”

Your session token (the STTAuthorization header).

STT_BASE_URL

No

https://api.sports-tracker.com/apiserver/v1

Sports Tracker API base endpoint.

Pass both through your MCP client's env block (as in Quick start); the server reads them from the process environment at startup.

NOTE

On STT_BASE_URL: your session token is sent as a header to whatever host this names. Leave it at the default unless you are deliberately pointing at a trusted local debugging proxy.


πŸ§‘β€πŸ’» Development

git clone https://github.com/wilkar/sports-tracker-mcp.git
cd sports-tracker-mcp
uv sync

Run the server from the clone:

STT_SESSION_KEY="your_key" uv run sport-tracker-mcp
# or keep it in a local .env (cp .env.example .env):
uv run --env-file .env sport-tracker-mcp

Point an MCP client at your working copy by swapping the --from target for an absolute path:

claude mcp add sports-tracker-dev -e STT_SESSION_KEY=your_key \
  -- uvx --from /absolute/path/to/sports-tracker-mcp sport-tracker-mcp

Tests, types and formatting:

uv run pytest
uv run mypy .
uv run isort --check .
uv run black --check .

Inspect the tool schemas:

uv run fastmcp list src/sport_tracker_mcp/server.py
uv run fastmcp dev inspector src/sport_tracker_mcp/server.py

Project structure

src/sport_tracker_mcp/
β”œβ”€β”€ client.py       # Async HTTP client with TTL cache & error handling
β”œβ”€β”€ config.py       # Environment variable resolution
β”œβ”€β”€ constants.py    # Activity ID mappings
β”œβ”€β”€ formatting.py   # Unit conversions (metric/imperial), pace, duration
β”œβ”€β”€ models.py       # Pydantic schemas for workouts, stats, load & recovery
β”œβ”€β”€ server.py       # FastMCP server, tool registration & UI cards
β”œβ”€β”€ tools.py        # Tool implementations
└── ui.py           # HTML rendering for tool-result cards

πŸ—ΊοΈ Roadmap

  • get_routes: List saved and recorded GPS routes with distances, speeds, and activity types.

  • get_route_details: GPS track waypoints, elevation profiles, and polyline coordinates for a route.

  • export_workout_gpx: Download standardized GPX XML track files for activities.

  • get_user_following: Retrieve followers and followed athlete profiles.


πŸ“„ License

This project is licensed under the MIT License.

Available Tools

8 tools
get_recent_activities_summaryGet Recent Activities SummaryC

Get a breakdown of activity frequency, total time spent, and last performed dates over the past N days.

Inputs: days, now_ts. Returns: days, activities, total_sessions

get_recent_workoutsGet Recent WorkoutsB

Get recent workouts with formatted distance, duration, pace, and HR.

Inputs: limit, imperial. Returns: result

get_social_feedGet Social FeedB

Get social feed items from followed athletes or community.

Inputs: limit, imperial. Returns: result

get_training_load_and_recoveryGet Training Load And RecoveryA

Get current training load, recovery hours, TSS, PTE, EPOC, and recovery status from the latest workout.

Inputs: no named parameters. Returns: peak_epoc, impact_tag, latest_sport, recovery_status, +6 more

get_training_summaryGet Training SummaryB

Get aggregated training volume, distance, time, and calories across sports for the past N days.

Inputs: days, now_ts, imperial. Returns: days, sports, workouts_count, total_distance_km, +3 more

get_user_statsGet User StatsA

Get lifetime totals and per-sport breakdown stats for the logged-in user or specified username.

Inputs: imperial, username. Returns: sports, total_days, total_workouts, total_distance_km, +3 more

get_vo2_max_historyGet Vo2 Max HistoryB

Get VO2Max and fitness age history extracted from recent workouts.

Inputs: limit. Returns: records, latest_vo2_max, average_vo2_max, latest_fitness_age

get_workout_detailsGet Workout DetailsC

Get detailed workout metrics including ascent, descent, HR zones, gear, and Suunto extensions.

Inputs: workout_key (required), imperial. Returns: gear, sport, avg_hr, max_hr, +20 more

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 8 tools

    Disambiguation4/5

    Most tools have clearly distinct purposes: social feed, workout lists, detailed workout metrics, user stats, VO2Max history, and recovery are easy to tell apart. The only mild ambiguity is between get_training_summary and get_recent_activities_summary, since both aggregate data over the past N days, though their metric focus differs.

    Naming Consistency5/5

    All tools follow a consistent get_<noun_phrase> snake_case pattern, making the set predictable and easy to navigate. There are no mixed conventions or vague verbs.

    Tool Count5/5

    Eight tools is well-scoped for a read-only sports tracking analytics server. Each tool represents a meaningful query surface without unnecessary redundancy or overwhelming breadth.

    Completeness4/5

    The read-only query surface is quite complete for analytics: recent workouts, detailed workout metrics, summaries, user stats, VO2Max history, recovery, and social feed are all covered. The main gap is the total absence of write operations like logging a workout or updating user data, though that may be acceptable if the server is intended only as a data retrieval layer.

    Maintenance

    ActivityMaintained
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      B
      quality
      D
      maintenance
      Enables users to interact with their Strava data through natural language to analyze workouts, track fitness progress, and explore routes. It supports retrieving detailed activity stats, heart rate data, and segment insights directly within AI assistants.
      26
      MIT
    • F
      license
      Not graded
      quality
      C
      maintenance
      Enables AI assistants to access and query Garmin Connect health and fitness data, including sleep, HRV, training load, and activities, with an optional coaching plugin for personalized training plans.
      4
      -
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables AI assistants to query live Garmin Connect health and fitness data, including daily metrics, activities, sleep analysis, and trends via natural language.
      MIT