Coach Mcp

coach-mcp

[CI] [License: MIT]

An opinionated AI training coach as an MCP server. It pulls your real data from Garmin Connect and prescribes with authority — science-based load management (ACWR), code-enforced injury gates (the server rejects plans that violate an active injury restriction, no matter what the LLM says), and persistent coaching memory so decisions, rationale, and your adaptation patterns survive between conversations. It will tell you "no" when your enthusiasm exceeds your capacity.

All health data and credentials stay on your machine — see Security & Privacy.

Quickstart

You need Python 3.12+, a free Garmin Connect account, and an MCP client (Claude Code, Claude Desktop, or Cursor).

Option A: uvx (recommended)

No install step — your MCP client runs the server on demand:

uvx garmin-coach-mcp

Jump to Connect your MCP client and use uvx as the command.

Option B: from source

git clone https://github.com/snoozelieb/coach-mcp.gitcd coach-mcp
python -m venv .venv# Linux/macOS:source .venv/bin/activate# Windows:.venv\Scripts\activate
pip install -r requirements.txtcp .env.example .env   # then edit: GARMIN_EMAIL, GARMIN_PASSWORDpython server.py

Connect your MCP client

The server needs two environment variables: GARMIN_EMAIL and GARMIN_PASSWORD. Optional: COACH_DATA_DIR (where your coaching data lives); COACH_TOKEN_DIR, COACH_TRANSPORT and COACH_CODE_MODE are covered under Security & Privacy and Advanced. From a source checkout, a .env file works too.

To run the server or the helpers from a terminal, set the two variables in that shell first. PowerShell and bash quote differently:

$env:GARMIN_EMAIL = "[email protected]"$env:GARMIN_PASSWORD = "your-password"

export [email protected] GARMIN_PASSWORD=your-password

Claude Code

claude mcp add coach-mcp \  --env [email protected] \  --env GARMIN_PASSWORD=your_garmin_password \  -- uvx garmin-coach-mcp

Or in .mcp.json (Claude Code expands ${VAR} from your shell environment, so a committed file holds no secret):

{  "mcpServers": {    "coach-mcp": {      "command": "uvx",      "args": ["garmin-coach-mcp"],      "env": {        "GARMIN_EMAIL": "[email protected]",        "GARMIN_PASSWORD": "${GARMIN_PASSWORD}",        "COACH_DATA_DIR": "/path/to/your/coach-data"      }    }  }}

Running from source instead: claude mcp add coach-mcp -- python /full/path/to/coach-mcp/server.py

Claude Desktop

In claude_desktop_config.json (Settings → Developer → Edit Config):

{  "mcpServers": {    "coach-mcp": {      "command": "uvx",      "args": ["garmin-coach-mcp"],      "env": {        "GARMIN_EMAIL": "[email protected]",        "GARMIN_PASSWORD": "your_garmin_password",        "COACH_DATA_DIR": "/path/to/your/coach-data"      }    }  }}

Cursor

In .cursor/mcp.json (project) or ~/.cursor/mcp.json (global):

{  "mcpServers": {    "coach-mcp": {      "command": "uvx",      "args": ["garmin-coach-mcp"],      "env": {        "GARMIN_EMAIL": "[email protected]",        "GARMIN_PASSWORD": "your_garmin_password",        "COACH_DATA_DIR": "/path/to/your/coach-data"      }    }  }}

If you installed with pip install garmin-coach-mcp instead of uvx, use "command": "garmin-coach-mcp" with no args in any of the blocks above.

First run

1. Create your profile. Run the interactive wizard (installed copies have the console script; a source checkout can run the script):

   bash

   garmin-coach-setup                 # pip / uvx installpython scripts/setup_wizard.py     # source checkout

   Until a profile exists the server runs in setup mode: plan, program and push writes answer setup_required and name the data directory they looked in.

   It creates your athlete profile, training config, and empty plan/memory files in the data directory. Alternatively, create the two required files by hand and let the coach fill in the rest via conversation:

   bash

   echo '{"personal":{"name":null},"injury_history":[],"life_constraints":{}}' > data/athlete.jsonecho '{"events":[],"current_block":{"phase":"base"}}' > data/training_config.json

2. Pull your Garmin baseline. In your MCP client, say:

   "Run refresh_athlete_baseline and set up my training."

   The coach pulls your name, weight, age, HR data, and training capacity from Garmin, then starts the onboarding conversation — goals, constraints, injury history, race calendar.

3. Garmin MFA / expired session. Garmin logins are token-cached. If tools start returning AUTH_REQUIRED, recover with:

   bash

   garmin-coach-login                 # pip / uvx installpython scripts/garmin_login.py     # source checkout

   It does a fresh credential login, prompts for the MFA code if Garmin asks, and saves new tokens. Restart the MCP server afterwards.

How it works

1. Snapshot first — every coaching conversation starts from get_coaching_snapshot(): current time context, 7-day week grid (rest days explicit), fitness metrics, plan adherence, open anomalies, injuries, sleep gate.
2. Load hierarchy before prescribing — overall ACWR (injury gate, 0.8–1.3 sweet spot), then sport-specific ACWR (spike detection), then sport-specific CTL (race readiness).
3. Hard gates are code, not vibes — update_weekly_plan and push_plan_to_garmin reject sessions that violate an active injury's restricted activities, and every non-rest session must carry a purpose or the save is refused. Multi-week programs (training_program) are rejected if their starting capacity contradicts your actual history.
4. Grounded in what you've actually done — prescriptions are anchored to your demonstrated per-sport capacity from recent sessions, not template numbers; a weekly plan that outruns that history comes back with grounding_warnings.
5. Curiosity with memory — planned-vs-actual anomalies (missed session, type mismatch, activity on a rest day) register once with a lifecycle (open → asked → resolved); the coach asks you what happened instead of silently assuming.
6. Everything persists — decisions, approvals, adaptation patterns, and season lifecycle (race debriefs, phase transitions) live in local JSON and carry across sessions.

MCP surface

52 tools — you don't call them directly; the coach uses them during conversation:

Every tool carries MCP annotations (read-only / destructive / idempotent / open-world), enforced by tests.

6 prompts: weekly_planning, morning_brief, injury_assessment, week_review, onboarding, race_program.

6 resources: coach://athlete/profile, coach://plan/current, coach://config/training, coach://coaching/decisions, coach://context/now, coach://coaching/doctrine (the long-form coaching doctrine).

Security & Privacy

Everything stays on your machine:

• Credentials: GARMIN_EMAIL/GARMIN_PASSWORD live in your MCP client config or a local .env. Garmin OAuth tokens are cached in a local token store (.garth/ in a source checkout, a per-user garmin-tokens directory for installed copies; override with COACH_TOKEN_DIR).
• Health data: all coaching data (profile, plans, fitness history, sleep, coaching memory) is local JSON in your data directory. There is no backend, no telemetry, no analytics.
• What leaves your machine: requests to Garmin's own API (your credentials/tokens, sent only to Garmin); whatever your MCP client sends to its LLM as part of the conversation; optional public web-page fetches when the coach researches a race, injury, or exercise. Nothing else: the FastMCP startup banner that would check PyPI for updates is disabled.
• Single athlete per data directory by design. For multiple athletes, run separate server instances with separate COACH_DATA_DIRs.

See SECURITY.md for details and how to report issues.

Data directory

Resolution order: COACH_DATA_DIR env var → data/ in a source checkout → a per-user data directory (created on first run for installed packages). The only file shipped with the package is methodology.json (safety rules, race templates, personas); everything personal is created locally and never committed.

Advanced

# HTTP transport (streamable-http) instead of stdioCOACH_TRANSPORT=streamable-http FASTMCP_PORT=8000 garmin-coach-mcp
# Code Mode (search/execute meta-tools instead of 52 individual tools)pip install fastmcp[code-mode]COACH_CODE_MODE=1 garmin-coach-mcp
# Standalone morning auditpython scripts/daily_loop.py          # ingest + audit yesterday + template brief (exit 1 if unverified)
# Tests (1,546 tests; clean checkouts use committed sanitized fixtures)pip install -r requirements-dev.txtpython -m pytest -q

Architecture

coach/server.py registers tools from the coach/ package (11 tool modules, pure parsers, a typed pydantic storage layer, CTL/ATL/ACWR fitness math, a Garmin client with token-first auth, and a workout builder that pushes structured workouts to your watch). The project went through a five-phase modernization — auth rebuild, schema layer, hard gates, sectioned snapshot, packaging — whose full history and rationale live in docs/UPGRADE_ROADMAP.md. Development conventions are in CLAUDE.md.

Acknowledgements

All Garmin Connect access — login, MFA, token handling, activity and health data, and workout upload — runs on python-garminconnect by Ron Klinkien (@cyberjunky) and its contributors (MIT). coach-mcp wouldn't exist without it.

License

MIT