Polar MCP Server
An MCP 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.
README
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:
- In Claude: Settings → Integrations → Add MCP Server
- Enter the URL:
https://polar-mcp-server.n-neuhaeusel.workers.dev/mcp - Claude will open an authorization window — log in with your Polar account
- 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 deploy
After deploying, add the callback URL to your Polar app:
https://YOUR-WORKER.workers.dev/callback
Option 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 auth
Add 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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.