Health4AI
health4.ai — Apple Health × AI
What it does
iPhone HealthKit → Your Postgres database → MCP server → Any AIApple Health holds years of your biometric data — sleep stages, HRV, heart rate, workouts, VO₂ max, and 150+ other metrics. health4.ai makes all of it queryable from Claude, ChatGPT, Cursor, Ollama, or any MCP-compatible client via 8 purpose-built tools.
You control the data. It syncs to a Postgres database you configure — Supabase, Neon, or a local Docker container. health4.ai never stores or has access to your health data.
Related MCP server: oura-ring-mcp
Why it exists
Problem | health4.ai fix |
Apple has no HealthKit server API — all access requires an on-device app | Native iOS app with |
Health Auto Export only works on the same WiFi | Your data lands in Postgres — queryable from any AI, anywhere |
The claude.ai Apple Health connector doesn't reach Claude Code CLI or Cursor | Standard MCP (stdio) — one config block works everywhere |
Most solutions require a managed cloud service | Bring your own Postgres: Supabase, Neon, or fully local |
Demo
Demo video coming. Here's what a typical conversation looks like:
You: How was my recovery this week? Anything standing out?
Claude: Your recovery this week was mixed but trending positive.
• HRV averaged 58ms (Tue–Thu strong at 64–68ms; Monday low at 44ms after Saturday's long run)
• Sleep averaged 7h 12m — Wednesday and Thursday were your best nights (7h 40m+)
• Resting HR dropped from 54bpm Monday to 49bpm Friday — a good sign
Recommendation: today looks like a solid day for a moderate-intensity session.Quick start
Choose your Postgres backend first:
# 1. Create a project at supabase.com
# 2. Run the schema
psql "$DATABASE_URL" < web/public/schema.sql
# or use the Supabase dashboard SQL editor# 1. Create a project at neon.tech
# 2. Run the schema
psql "$DATABASE_URL" < web/public/schema.sqldocker run -d \
--name health4ai-postgres \
-e POSTGRES_PASSWORD=yourpassword \
-p 5432:5432 \
postgres:16
psql "postgresql://postgres:yourpassword@localhost:5432/postgres" \
< web/public/schema.sqlThen set up the MCP server:
git clone https://github.com/jefflitt1/health4ai.git
cd health4ai
cp mcp-server/.env.example mcp-server/.envEdit mcp-server/.env:
DATABASE_URL=postgresql://... # your Postgres connection string
HEALTHKIT_USER_ID=your_user_id # any string to identify your dataAdd to your AI client:
{
"mcpServers": {
"health4ai": {
"command": "python",
"args": ["/path/to/health4ai/mcp-server/main.py"],
"env": {
"DATABASE_URL": "postgresql://...",
"HEALTHKIT_USER_ID": "your_user_id"
}
}
}
}Same block → ~/.cursor/mcp.json
Pair with mcphost or mcp-client-for-ollama:
mcphost --model ollama/llama3.2 \
--mcp-server "health4ai:python /path/to/health4ai/mcp-server/main.py"Your health data and the model both stay on your hardware — nothing leaves your machine.
Install the iOS app: TestFlight link coming at App Store launch. Sign in with your database credentials and tap Start Sync.
MCP tools
Tool | What it answers |
| Overview of key metrics for the past N days |
| Per-night sleep breakdown with REM, Deep, Core stages |
| Daily HRV (SDNN) with rolling comparison and trend |
| Everything recorded for a specific date |
| Recent workouts with type, duration, distance, calories |
| Raw time-series for any HealthKit metric type |
| Monthly aggregates over years (raw + summary tiers) |
| Recovery status, sleep quality, training load, fitness markers |
| Find days where a metric crossed a threshold |
| Personal baseline: min/max/mean/percentiles |
| Compare a metric between two date ranges |
Architecture
┌─────────────────────────────────────────────────────────────┐
│ iPhone │
│ HKObserverQuery + BGTaskScheduler │
│ → continuous background sync │
└──────────────────────────┬──────────────────────────────────┘
│ HTTPS
▼
┌─────────────────────────────────────────────────────────────┐
│ Your Postgres database (Supabase / Neon / local Docker) │
│ healthkit_metrics · healthkit_daily_summaries │
│ v_healthkit_daily_quantity (unified view) │
└──────────────────────────┬──────────────────────────────────┘
│ SQL (service-role key, server-side only)
▼
┌─────────────────────────────────────────────────────────────┐
│ FastMCP server (mcp-server/main.py) │
│ 11 tools · stdio transport │
└──────────────────────────┬──────────────────────────────────┘
│ MCP
▼
Claude · ChatGPT · Cursor · Ollama · any clientData tiers: queries within the last 30 days return raw samples; older data transparently switches to pre-aggregated daily summaries — so long-term trend queries stay fast regardless of data volume.
Repo structure
health4ai/
├── ios/ # Swift/SwiftUI iOS app (iOS 17+)
│ └── Health4AI/ # HealthKit sync engine, auth, settings
├── mcp-server/
│ ├── main.py # FastMCP server entry point
│ ├── tools.py # 11 tool implementations
│ └── .env.example # Required environment variables
├── web/
│ ├── public/schema.sql # Portable Postgres schema (all backends)
│ └── src/ # Astro marketing site
├── scripts/
│ ├── import_health_export.py # One-time XML backfill from Apple Health export
│ └── summarize_historical.py # Backfill daily summaries table
└── docs/
└── SETUP.md # Detailed setup guidePrivacy
Your health data goes directly from your iPhone to your Postgres database. health4.ai never receives, stores, or has access to it. The MCP server runs locally with your own credentials — your data never touches our infrastructure.
See the Privacy Policy for full details.
Contributing
MIT licensed. PRs welcome.
Good first areas: additional metric aggregations, multi-user support with JWT/RLS, Android, and more MCP client integration guides.
License
MIT — see LICENSE.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseAqualityAmaintenanceLocal-first MCP server that reads Apple Health export files (export.xml/zip) and exposes activity, sleep, HRV, and workout data to AI agents, keeping all data on your machine.Last updated184721MIT
- Alicense-qualityBmaintenanceProvides natural-language access to Oura health data through Claude, with a local SQLite mirror and MCP tools for analyzing patterns with personal annotations.Last updated953MIT
- AlicenseAqualityAmaintenanceAn MCP server that enables AI agents to query Apple Health data (190+ metrics) in natural language, including trends, comparisons, and structured exports.Last updated7772MIT
- Alicense-qualityAmaintenanceRead-only MCP server that exposes Apple Health data (steps, workouts, sleep, etc.) from a local SQLite store, allowing AI agents to query health metrics without sending data to hosted services.Last updated3Apache 2.0
Related MCP Connectors
63 tools for Apple Health, Fitbit, Oura & Health Connect data in Claude, ChatGPT, Grok & Mistral.
Garmin data in Claude: 135 tools — activities, sleep, HRV, training, workouts. Free, open source.
WHOOP recovery, strain, sleep and workouts in Claude via official WHOOP OAuth. Free, open source.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/jefflitt1/health4ai'
If you have feedback or need assistance with the MCP directory API, please join our Discord server