Skip to main content
Glama
charlesfrisbee

Garmin Workouts MCP

by charlesfrisbee
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Local

Garmin Workouts MCP

Create Garmin Connect workouts using natural language descriptions. Built as an MCP (Model Context Protocol) server.

Installation

Claude Code (Recommended)

claude mcp add garmin-workouts-mcp npx garmin-workouts-mcp

Claude Desktop

Add to your configuration file:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

  • Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "garmin-workouts-mcp": {
      "command": "npx",
      "args": ["-y", "garmin-workouts-mcp"]
    }
  }
}

Then restart Claude Desktop.

Related MCP server: Garmin Workout Pipeline

Usage

⚠️ Important: Garmin's auth tokens expire after ~5 minutes. Plan multiple workouts and create them all in one session.

Quick Start

  1. Request a workout - Just describe what you want: "Create a 10 min warmup, 5x1km threshold intervals with 2 min rest, then 10 min cooldown"

  2. Authenticate when needed - A browser window will open to Garmin Connect for you to log in (happens when tokens expire ~every 5 minutes)

  3. Your workout appears - The tool creates it directly in your Garmin Connect account and provides a link to view it

  4. Available on device - The workout will be available in Garmin Connect and can be sent to your device from there

Your login is temporarily saved - Tokens are stored securely on your machine but expire after ~5 minutes, so you may need to re-authenticate between sessions.

Create multiple workouts in one session:

"Create these 3 workouts:
1. Easy 30 min run in zone 2
2. 5x1km threshold intervals with 2 min rest
3. 10x30 second sprints with 90 second recovery"

How It Works

  1. Request workouts - Describe what you want to create

  2. Auto-authentication - Browser opens for login when tokens expire

  3. Batch creation - Create multiple workouts in the same session

Example Workouts

  • Easy run: "30 minute easy run in zone 2"

  • Intervals: "5x400m at 5k pace with 60 second rest"

  • Threshold: "10 min warmup, 20 min tempo in zone 4, 10 min cooldown"

  • Sprints: "Warmup 10 min, then 8x15 second sprints with 3 min recovery"

  • Complex: "Pyramid workout: 1-2-3-4-3-2-1 minutes hard with equal recovery"

Features

  • 🧠 Natural language processing - Describe workouts in plain English

  • 🔐 Secure authentication - Token-based auth with automatic renewal

  • 🏃 Multi-sport support - Running, cycling, and swimming workouts

  • ⚡ Direct Garmin integration - Creates workouts instantly in Garmin Connect

  • 💾 Smart token handling - Automatic re-authentication when tokens expire

Current Limitations

⚠️ Heart rate/zone targets only - The tool currently supports heart rate zones (Zone 1-5) and specific BPM targets, but does not yet support pace-based targets (e.g., 4:00/km).

How It Works

  1. Converts your natural language workout description into structured data

  2. Translates to Garmin's workout API format with proper zones and targets

  3. Creates the workout directly in your Garmin Connect account

  4. Syncs automatically to your Garmin device

Made for Claude Code and Claude Desktop.

Legal Disclaimer

This project is an unofficial third-party tool that interacts with Garmin Connect's web interface. It is not affiliated with, endorsed by, or sponsored by Garmin Ltd. or any of its affiliates.

  • Use at your own risk - This tool may stop working if Garmin changes their API or terms of service

  • Not for commercial use - This is a personal project intended for individual use only

  • No warranty - The software is provided "as is" without any guarantees

  • Respect Garmin's terms - Users are responsible for complying with Garmin Connect's terms of service

  • Data responsibility - You are responsible for the workouts created and any data shared with Garmin

If you represent Garmin and have concerns about this project, please reach out through GitHub issues.

Development

Token Storage

Auth tokens are stored securely in:

  • Location: ~/.config/garmin-workouts-mcp/auth.json

  • Permissions: 600 (user read/write only)

  • Expiry: ~5 minutes from login

  • Content: JWT tokens and cookies for Garmin Connect API

Local Development

# Clone and install
git clone https://github.com/charlesfrisbee/garmin-workouts-mcp.git
cd garmin-workouts-mcp
pnpm install

# Build and test locally
pnpm run build
pnpm run pack

# Add to Claude Code for testing
claude mcp add garmin-workouts-mcp ./garmin-workouts-mcp-local.tgz

Requirements

  • Node.js 16+

  • pnpm

  • Claude Code (for local testing)

  • Garmin Connect account

Available Tools

3 tools
authenticate_garminB

Authenticate with Garmin Connect (opens browser)

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

B3.1/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full burden. It discloses that authentication opens a browser, which is useful behavioral context. However, it omits critical details like whether this is a one-time setup, if it stores tokens, error handling, or rate limits. For an auth tool, this is a significant gap in transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that front-loads the core action ('Authenticate with Garmin Connect') and adds a key behavioral detail ('opens browser') without waste. It's appropriately sized for a simple tool with no parameters.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of authentication (often involving tokens, permissions, or errors) and no annotations or output schema, the description is incomplete. It lacks details on what happens after authentication, success/failure responses, or how it integrates with sibling tools. For an auth tool, this leaves significant gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There are 0 parameters, and schema description coverage is 100%, so no parameter documentation is needed. The description doesn't add param info, but with no params, a baseline of 4 is appropriate as it doesn't need to compensate for gaps.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Authenticate with') and target ('Garmin Connect'), specifying it opens a browser. It distinguishes from siblings like 'check_garmin_auth' (verification) and 'create_garmin_workout' (creation), though it doesn't explicitly contrast them. The purpose is specific but could be more differentiated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., needing credentials), when authentication is required, or how it relates to sibling tools like 'check_garmin_auth'. The description implies usage for initial auth but lacks explicit context or exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

check_garmin_authB

Check if Garmin authentication is valid

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

TDQS

B3.1/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool checks authentication validity but doesn't describe what 'valid' means (e.g., token expiration, scope sufficiency), what happens on failure, or any side effects like rate limits or logging. This leaves significant gaps for a tool that likely interacts with external APIs.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that directly states the tool's purpose without unnecessary words. It's appropriately sized and front-loaded, making it easy to understand at a glance.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (involving external authentication checks) and lack of annotations and output schema, the description is incomplete. It doesn't explain what constitutes valid authentication, potential error conditions, or return values, leaving the agent with insufficient information for reliable use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has 0 parameters with 100% schema description coverage, so the schema fully documents the absence of inputs. The description doesn't need to add parameter details, and it correctly implies no inputs are required for checking auth status, aligning with the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose as checking Garmin authentication validity, using a specific verb ('check') and resource ('Garmin authentication'). However, it doesn't differentiate from sibling tools like 'authenticate_garmin' which might handle initial authentication versus checking existing validity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives like 'authenticate_garmin' for initial setup or 'create_garmin_workout' for operations requiring valid auth. The description implies usage for checking validity but lacks explicit context or exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

create_garmin_workoutB

Create a workout in Garmin Connect from structured workout data. Claude should parse the natural language description and pass structured workout steps.

ParametersJSON Schema
NameRequiredDescriptionDefault
nameYesName of the workout
sportYesSport type (defaults to running)
stepsYesArray of workout steps

TDQS

B3.3/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. While it mentions the creation action, it doesn't disclose critical behavioral traits such as authentication requirements (implied by sibling tools but not stated), potential side effects (e.g., whether this persists data or requires confirmation), error handling, or rate limits. The description is minimal and lacks necessary operational context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is appropriately sized with two sentences that are front-loaded with the main purpose. Every sentence earns its place by stating the tool's function and its role in the workflow, though it could be slightly more structured for clarity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of a creation tool with no annotations and no output schema, the description is incomplete. It lacks details on authentication needs (implied by siblings but not stated), behavioral traits, error responses, or what happens post-creation. For a mutation tool, this leaves significant gaps in understanding how to use it effectively.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all parameters thoroughly. The description doesn't add any additional meaning beyond what's in the schema (e.g., it doesn't explain parameter interactions or provide examples not in the schema). Baseline 3 is appropriate as the schema does the heavy lifting, but no extra value is added.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the specific action ('Create a workout in Garmin Connect') and resource ('from structured workout data'), distinguishing it from sibling tools like authenticate_garmin and check_garmin_auth. It explicitly mentions the tool's role in the workflow: Claude should parse natural language and pass structured data.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage by stating 'Claude should parse the natural language description and pass structured workout steps,' suggesting this tool is used after natural language processing. However, it doesn't explicitly state when to use this tool versus alternatives or provide exclusions, leaving some ambiguity about its specific context in relation to sibling tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. 3 tool updatesv1.0.0
    • First observedauthenticate_garmin
    • First observedcheck_garmin_auth
    • First observedcreate_garmin_workout
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

B3.4/5.0
Disambiguation5/5

Each tool has a clearly distinct purpose: authentication initiation, authentication status verification, and workout creation. There is no overlap in functionality, and an agent can easily differentiate between them based on their names and descriptions.

Naming Consistency5/5

All tools follow a consistent verb_noun pattern with 'garmin' as a prefix: authenticate_garmin, check_garmin_auth, create_garmin_workout. The naming is uniform and predictable across the set.

Tool Count3/5

With only 3 tools, the set feels thin for a workout management server. While authentication and creation are covered, there are likely gaps such as retrieving, updating, or deleting workouts, which are common operations in this domain.

Completeness2/5

The tool surface is significantly incomplete for workout management. It lacks essential operations like getting existing workouts, updating workouts, deleting workouts, or listing workouts, which are critical for a full CRUD lifecycle. Agents will face dead ends when trying to manage workouts beyond creation.

Maintenance

ActivityInactive
ResponsivenessSyncing

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

  • garmin-mcp

    yashhooda1
    A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI assistants to read Garmin activities and create/schedule structured workouts and multi-week training plans on Garmin Connect, syncing to the user's watch.
    1
    MIT

  • garmin-mcp

    yashhooda1
    A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI assistants to read Garmin activities and create/schedule structured workouts and multi-week training plans directly on Garmin Connect, syncing to your watch with guided prompts.
    1
    MIT

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/charlesfrisbee/garmin-workouts-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server