Open-source registry·8 open connectors

The wellness layer
for AI agents.

Open-source MCP connectors for WHOOP, Oura, Garmin, Strava, Fitbit, Withings, Apple Health and Polar. Use them in Claude, Cursor, ChatGPT, Hermes or any MCP client. Agents never receive your tokens.

WHOOP
Oura Ring
Garmin Connect
Strava
Fitbit
Withings
Apple Health
Polar

Works with every MCP-compatible client

Claude DesktopCursorWindsurfHermesOpenClawChatGPT DesktopCustom MCP agentsCodexClaude DesktopCursorWindsurfHermesOpenClawChatGPT DesktopCustom MCP agentsCodex
9connectors
Read-onlyby default
MITlicensed
0hosted vaults
~60sfirst setup

Real-world context

Built for real training days.

Delx Wellness is not another dashboard. It turns the signals from your devices into useful context when an agent is helping with training, recovery and daily planning.

sleeprecoverytraining
Healthy adults training in a refined dark gym while checking wearable recovery data
Strength + readiness

Train

Recovery, HRV and training load become context before the workout starts.

Healthy adults running and cycling outdoors at sunrise with generic wearable devices
Outdoor cardio

Move

Runs, rides and routes stay provider-tagged for cleaner agent reasoning.

Fit adults stretching in a calm home training space near abstract wellness charts
Mobility + sleep

Recover

Your assistant can connect today's plan with yesterday's recovery.

How it works

From health signal to AI context in three steps.

Each connector is a standalone npm package. Local-first by design, read-only by default, privacy modes built in.

01

Install

One npx command per connector. No global install, no Docker, no servers to babysit.

$ npx -y whoop-mcp-unofficial setup
02

Authorize

Browser-based OAuth or local helper. Tokens are saved to ~/.<provider>-mcp/ with chmod 600.

$ npx -y whoop-mcp-unofficial auth
03

Ask your agent

Drop the snippet into Claude Desktop, Cursor, Hermes or any MCP client. Your AI now has provider-tagged health context.

$ Should I train hard today?

Connectors

Every connector gets one elegant home.

8 public connectors stay independently installable, read-only by default, and tagged agent_ready in the registry. Private labs can live beside them without exposing sensitive provider details.

WHOOP

whoop-mcp-unofficial
agent_ready
WHOOP logo

Recovery score, HRV, sleep stages and day strain.

RecoveryHRVSleepStrainWorkouts
OAuth 2.0
Details

Oura Ring

oura-mcp-unofficial
agent_ready
Oura

Daily readiness, sleep periods, HRV trend and SpO2.

ReadinessSleepActivityHRVSpO2
OAuth 2.0
Details

Garmin Connect

garmin-mcp-unofficial
agent_ready
Garmin

Body Battery, training readiness, sleep, HRV and stress.

SleepHRVBody BatteryStressTraining Readiness
Local Garmin Connect
Details

Strava

strava-mcp-unofficial
agent_ready
Strava

Runs, rides, swims, segments and per-second activity streams.

ActivitiesStreamsRoutesAthlete Stats
OAuth 2.0
Details

Fitbit

fitbit-mcp-unofficial
agent_ready
Fitbit

Activity, sleep stages, intraday heart and HRV.

ActivitySleepHeart RateHRVSpO2Weight
OAuth 2.0
Details

Withings

withings-mcp-unofficial
agent_ready
Withings logo

Smart-scale composition, sleep stages and ECG-grade heart records.

Body MeasuresSleepActivityHeart Records
OAuth 2.0 signed
Details

Apple Health

apple-health-mcp-unofficial
agent_ready
Apple

Reads your local Apple Health export with no live HealthKit dependency.

ActivitySleepHeart RateHRVWorkouts
Local export.zip
Details

Polar

polar-mcp-unofficial
agent_ready
Polar logo

Nightly Recharge, training load, PPI/HRV and continuous samples.

Nightly RechargeTraining SessionsPPI SamplesSleepContinuous HR
OAuth 2.0
Details

Exercise Catalog

exercise-catalog-mcp-private
private_lab
Exercise Catalog

Private exercise catalog bridge for agent-built workouts.

ExercisesMuscle GroupsEquipmentVideo GuidanceWorkout Builder
Private provider token
Details

Quick start

Starter snippets for every client.

Pick your MCP client below, paste a snippet, then run setup for the connectors you actually use.

claude_desktop_config.json
{
  "mcpServers": {
    "whoop":   { "command": "npx", "args": ["-y", "whoop-mcp-unofficial"] },
    "oura":    { "command": "npx", "args": ["-y", "oura-mcp-unofficial"] },
    "garmin":  { "command": "npx", "args": ["-y", "garmin-mcp-unofficial"] },
    "strava":  { "command": "npx", "args": ["-y", "strava-mcp-unofficial"] },
    "fitbit":  { "command": "npx", "args": ["-y", "fitbit-mcp-unofficial"] },
    "withings":{ "command": "npx", "args": ["-y", "withings-mcp-unofficial"] },
    "apple_health": { "command": "npx", "args": ["-y", "apple-health-mcp-unofficial"] },
    "polar":   { "command": "npx", "args": ["-y", "polar-mcp-unofficial"] }
  }
}

In your AI

Your body, in your AI's context.

Stop pasting numbers from five apps. Ask once. Your agent reasons across providers in real time.

Claude Desktop
Should I train hard today? Use my wearable data.
Calling toolwhoop_daily_summary
Calling tooloura_daily_summary
Calling toolgarmin_daily_summary

No — go light. Your signals are mixed-to-yellow today.

  • whoop recovery 48% (avg 7d: 64%), HRV 42 ms vs 53 baseline
  • oura readiness 71, sleep score 78
  • garmin Body Battery 42, training readiness 56 (moderate)

Suggestion: zone-2 cardio 30–40 min, mobility, sleep priority. Re-evaluate tomorrow with whoop_daily_performance_coach.

Not medical advice.

Privacy & security

Your data stays on your machine.

Health data is sensitive — these connectors are built to treat it that way. There is no hosted layer in this registry. There is no place to leak your data, because there is no place to put it.

A private wellness data workspace with wearable metrics, local files and agent-ready context

Local-first storage

OAuth tokens are saved in ~/.<provider>-mcp/ with chmod 600. Nothing is uploaded to a hub. No third-party vault.

Read-only by design

No upload scopes are requested. The MCP client never receives access or refresh tokens. Tools never echo secrets.

Built-in audit

Every connector ships *_privacy_audit and *_connection_status tools so agents can verify posture without calling the upstream API.

Privacy modes

summary / structured / raw — defaults are conservative. Raw upstream payloads and GPS coordinates are explicit opt-in.

Not medical advice. These connectors expose user-authorized data for personal AI workflows. They are not medical devices and do not provide diagnosis, treatment or emergency monitoring.

FAQ

Questions, answered.

What is MCP?

Model Context Protocol — an open standard for connecting AI assistants to external tools and data. Once a server speaks MCP, compatible clients such as Claude Desktop, Cursor, ChatGPT Desktop, Hermes and custom agents can use its tools.

Why local-first instead of a hosted hub?

Health data is sensitive. Hosted hubs concentrate secrets and become attractive targets. The connectors here run on your machine, store tokens locally with chmod 600, and never share them with the MCP client. A hosted layer may exist later, but it will be a separate, opt-in product.

Can I install all eight at once?

Yes, but you probably should start with the providers you already use. The packages are independent and coexist cleanly. When two providers cover the same signal, each tool returns provider-tagged data so your agent can reconcile them.

Are these official?

No. Every connector is unofficial and not affiliated with the device makers. They use public APIs where available; Garmin uses the user's own Garmin Connect login locally, and Apple Health reads a manual export.zip rather than live HealthKit.

Is this medical advice?

No. These connectors expose user-authorized data for personal AI workflows. They are not medical devices and do not provide diagnosis, treatment or emergency monitoring. Always consult qualified professionals for medical concerns.

Can I contribute a new provider?

Yes — the connector quality standard documents the bar (registry_ready / agent_ready). Open an issue or PR on the delx-wellness repo with the provider you want to add and the data you'd expose.

Bring your physiology
to your prompt.

Eight open-source connectors. One local-first setup. Your AI can reason over sleep, recovery, activity and training context.