Health tracking MCP servers

A server here personal health data from wearables: sleep, heart rate, glucose.

Not here: workout plans.

146servers
62 remote84 localTagged by Odel's AI, which can make mistakes
By GitHub stars, at most two per publisher
  1. Number 1: Apple Health@neiltron/apple-health-mcpLocal-first Apple Health MCP server for questions about your sleep, workouts and heart data.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.571 GitHub stars.
  2. Number 2: WHOOP@shashankswe2020-ux/whoopMCP server for WHOOP health data — recovery, sleep, workouts, cycles, and trends.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.165 GitHub stars.
  3. Number 3: Whoop@briangaoo/whoop-mcpFull read + write access to your Whoop fitness data via the private iOS API. 48 tools.29% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.127 GitHub stars.

Best fit

113 made for this, ranked by starsRemoteLocal
  1. Totem @briangaoo/totemTotem — talk to your wearables with AI. Today: full Whoop access (48 tools).28% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.126 GitHub stars.
  2. Totem @thebriangao/totemTotem — talk to your wearables with AI. Today: full Whoop access (48 tools).7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.125 GitHub stars.
  3. Coach Watts @coachwatts/coach-wattsRemote MCP server for training, nutrition, wellness, and performance data with OAuth 2.0.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.95 GitHub stars.
  4. Google Health @davidmosiah/google-health-mcpPrivacy-first unofficial Google Health API v4 MCP server for health, sleep, activity, HR agents5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.66 GitHub stars.
  5. Cronometer @rwestergren/cronometer-api-mcpMCP server for Cronometer nutrition tracking — food logs, diary, macros, fasting3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.60 GitHub stars.
  6. Withings Health Data @akutishevsky/withingsMCP server for Withings health data — sleep, activity, heart, and body metrics.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.43 GitHub stars.
  7. Mi Fitness Data Bridge @shkyyy18/mi-fitness-data-bridgeLocal-first bridge: export your own Mi Fitness (Xiaomi) health data to SQLite/JSON/CSV and MCP.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.35 GitHub stars.
  8. Suunto MCP @googlarz/suunto-mcpSuunto watch data (workouts, sleep, recovery, 24/7 activity) for Claude and other AI assistants.Not assessed yet.Runs on your machine, installed from npm.31 GitHub stars.
  9. HealthClaw Guardrails @aks129/healthclaw-guardrailsGuardrailed FHIR access for AI agents: PHI redaction, audit trail, step-up auth, tenant isolation7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.31 GitHub stars.
  10. Oura Ring @mitchhankins01/oura-ring-mcpConnect your Oura Ring to Claude AI assistants. Health metrics with smart analysis tools.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.29 GitHub stars.
  11. Cronometer @cphoskins/cronometerMCP server for Cronometer — food logs, macros, fasting, biometrics, and recurring foods10% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.24 GitHub stars.
  12. Polar Health Data (self-hosted) @stumason/polar-flow-serverSelf-hosted Polar health analytics with a built-in MCP server: sleep, HRV, workouts, baselines.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.23 GitHub stars.
  13. Google Health Fitbit @berkkilicoglu/google-health-fitbit-mcpPrivacy-first Google Health API MCP server for health, sleep, activity and HR agents4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.18 GitHub stars.
  14. Bluetooth LE Health Sensors @k-dense-ai/labmcp-ble-healthMCP server for Bluetooth LE health sensors (standard GATT profiles).3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.17 GitHub stars.
  15. Samsung Health @davidmosiah/samsung-health-mcpUnofficial local-first MCP server for Samsung Health personal-data CSV/ZIP exports.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.15 GitHub stars.
  16. Run Coach @chenhunghan/garmin-mcp-appGarmin data with interactive charts: daily briefing, training trends, workout planning. Unofficial.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.14 GitHub stars.
  17. Whoop MCP Server @yuridivonis/whoop-mcp-serverYour WHOOP recovery, sleep, strain and workouts in Claude, ChatGPT or other MCP apps. Self-hosted.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.14 GitHub stars.
  18. WHOOP — MissingMCP @missingmcp/whoopWHOOP recovery, strain, sleep and workouts in Claude via official WHOOP OAuth. Free, open source.13% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.13 GitHub stars.
  19. Garmin — MissingMCP @missingmcp/garminGarmin data in Claude: 135 tools — activities, sleep, HRV, training, workouts. Free, open source.20% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.13 GitHub stars.
  20. InBody @rwestergren/inbody-api-mcpMCP server for InBody body-composition data — scans, body fat, muscle mass, body water4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.12 GitHub stars.
  21. Health Bridge for AI @roian6/health-bridgeApple Health AI Bridge provides read-only local MCP access for Health Bridge for AI.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.8 GitHub stars.

Also touches on Health tracking

33 where it is one part of a bigger job