polar-mcp-server
A Model Context Protocol (MCP) server that provides AI assistants with access to the Polar AccessLink API v3
Documentation
Polar MCP Server
An MCP (Model Context Protocol) server for the Polar AccessLink API. Connect your Polar fitness data to Claude AI - access workouts, sleep analysis, recovery metrics, heart rate data, and more.
Quick Start (Public Instance)
No setup required! Use our hosted instance:
1. In Claude: Settings → Integrations → Add MCP Server
2. Enter the URL: `https://polar-mcp-server.n-neuhaeusel.workers.dev/mcp`
3. Claude will open an authorization window — log in with your Polar account
4. Start chatting about your fitness data!
Features
25 Tools Available
| Category | Tools | Description |
|---|---|---|
| Exercises | `get_exercises`, `get_exercise` | Training data with HR, speed, zones |
| Exercise Export | `get_exercise_fit`, `get_exercise_tcx`, `get_exercise_gpx` | Export in FIT, TCX, GPX formats |
| Sleep | `get_sleep`, `get_sleep_range` | Sleep stages, score, duration |
| Recovery | `get_nightly_recharge`, `get_nightly_recharge_range` | ANS charge, HRV, breathing rate |
| Activity | `get_daily_activity`, `get_daily_activity_range`, `get_activity_samples`, `get_activity_samples_range` | Steps, calories, activity zones |
| Heart Rate | `get_continuous_heart_rate`, `get_continuous_heart_rate_range` | 24/7 heart rate monitoring |
| Training Load | `get_cardio_load`, `get_cardio_load_range`, `get_cardio_load_history` | TRIMP, acute/chronic load |
| SleepWise | `get_sleepwise_alertness`, `get_sleepwise_circadian_bedtime` | Alertness predictions, optimal bedtime |
| Biosensing | `get_body_temperature`, `get_skin_temperature`, `get_spo2` | Temperature, SpO2 data |
| User | `get_user_info`, `get_physical_info` | Profile, VO2max, resting HR |
Supported Devices
- Polar Pacer / Pacer Pro
- Polar Vantage V2 / V3
- Polar Vantage M / M2
- Polar Grit X / Grit X Pro / Grit X2 Pro
- Polar Ignite / Ignite 2 / Ignite 3
- Polar Unite
- And more...
Example Prompts
Once connected, ask Claude:
- "Show me my workouts from last week"
- "How was my sleep last night? Compare it to my weekly average"
- "Analyze my heart rate variability trends"
- "What's my current training load status?"
- "When should I go to bed tonight for optimal recovery?"
- "Export my last run as a GPX file"
- "How many steps did I take this month?"
Self-Hosting
Want to run your own instance? Two deployment options available:
Option 1: Cloudflare Workers (Recommended)
Prerequisites
- Cloudflare account
- Polar AccessLink API credentials
Setup
# Clone and install
git clone https://github.com/NelsonNew/polar-mcp-server.git
cd polar-mcp-server
npm install
# Create KV namespace
npx wrangler kv namespace create OAUTH_KV
# Copy the ID to wrangler.toml
# Set secrets
npx wrangler secret put POLAR_CLIENT_ID
npx wrangler secret put POLAR_CLIENT_SECRET
# Deploy
npm run deployAfter deploying, add the callback URL to your Polar app:
https://YOUR-WORKER.workers.dev/callbackOption 2: Local (Claude Desktop)
# Clone and build
git clone https://github.com/NelsonNew/polar-mcp-server.git
cd polar-mcp-server
npm install && npm run build
# Get access token
export POLAR_CLIENT_ID="your_client_id"
export POLAR_CLIENT_SECRET="your_client_secret"
npm run authAdd to Claude Desktop config (`~/Library/Application Support/Claude/claude_desktop_config.json`):
{
"mcpServers": {
"polar": {
"command": "node",
"args": ["/path/to/polar-mcp-server/dist/index.js"],
"env": {
"POLAR_ACCESS_TOKEN": "your_access_token"
}
}
}
}API Reference
All tools use the Polar AccessLink API v3.
| Tool | Endpoint | Description | ||
|---|---|---|---|---|
| `get_user_info` | `/users/{id}` | User profile | ||
| `get_physical_info` | `/users/physical-information` | VO2max, max HR, resting HR | ||
| `get_exercises` | `/exercises` | Last 30 days of workouts | ||
| `get_exercise` | `/exercises/{id}` | Single workout details | ||
| `get_exercise_fit/tcx/gpx` | `/exercises/{id}/fit\ | tcx\ | gpx` | Export formats |
| `get_sleep` | `/users/sleep` | Sleep data | ||
| `get_nightly_recharge` | `/users/nightly-recharge` | Recovery metrics | ||
| `get_daily_activity` | `/users/activities` | Daily activity | ||
| `get_continuous_heart_rate` | `/users/continuous-heart-rate` | 24/7 HR | ||
| `get_cardio_load` | `/users/cardio-load` | Training load | ||
| `get_sleepwise_alertness` | `/users/sleepwise/alertness` | Alertness predictions | ||
| `get_body_temperature` | `/users/biosensing/bodytemperature` | Body temp | ||
| `get_spo2` | `/users/biosensing/spo2` | Blood oxygen |
Troubleshooting
| Error | Solution |
|---|---|
| "Polar API error (403)" | Re-authorize or check if data sync is complete |
| "Polar API error (404)" | Endpoint not available for your device/subscription |
| No exercise data | Sync your Polar device to Polar Flow app first |
Privacy
- Your Polar credentials are never stored
- OAuth tokens are managed securely by the Cloudflare Workers OAuth provider
- Each user gets their own isolated MCP session
- No fitness data is logged or stored on our servers
Contributing
Contributions welcome! Please open an issue or PR.
License
MIT
Links
Frequently asked questions
What is polar-mcp-server?
polar-mcp-server is A Model Context Protocol (MCP) server that provides AI assistants with access to the Polar AccessLink API v3
How do I install polar-mcp-server?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is polar-mcp-server open source?
Yes — it is hosted on GitHub at https://github.com/NelsonNew/polar-mcp-server and has 5 stars.
Related MCP tools
Model Context Protocol Servers
The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra
A MCP for Claude Desktop / Claude Code / Windsurf / Cursor to build n8n workflows for you
MCP server to provide Figma layout information to AI coding agents like Cursor
The world's best AI personal assistant for email. Open source app to help you reach inbox zero fast.
Instant is the best backend for AI-coded apps. You get auth, permissions, storage, presence, and streams — everything you need to ship apps your users will love.
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP