marrow-mcp
Provides read-only access to Apple Health data, including daily health metrics, workouts with set-by-set strength detail, nutrition logs, and raw health samples.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@marrow-mcpwhat was my average heart rate during runs last week?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Marrow Health MCP server (marrow-mcp)
Let your AI agents read your own Apple Health data.
Marrow is a free iOS app that tracks 178 health data series - 172 Apple Health types plus its own meal diary and set-by-set weightlifting log. This repo is its self-hosted companion server: one Python file, standard library only, that keeps a SQLite mirror of your data on hardware you own and serves it over the Model Context Protocol so agents can query it 24/7, phone in your pocket.
Nothing here talks to a cloud. Data flows phone → your machine, full stop.

Run it
pip install "marrow-mcp[qr]" # [qr] adds segno, which draws the pairing QR
marrow-server --port 8800 --data ./data # prints a pairing URLWithout [qr] the pairing page shows the pairing JSON instead of a code.
or from a clone
python3 marrow_server.py # prints a pairing URL
python3 marrow_server.py --port 8800 --data ./dataor with Docker
docker compose up -dOpen the pairing URL on any screen, then in Marrow: Export, Server MCP,
Pair with a server, and scan. From then on the app's background pushes keep
the mirror current with the app closed. The app pairs over plain http only on
your own networks (a private or tailnet IPv4 address, a .local or .ts.net
name, a short LAN name). A public address needs https (--url https://...).
Upgrading to 0.3.0
Stop the old server and start the new one on the same --data directory.
An existing mirror.sqlite gains the new columns on first start, and the
tokens in --data carry over, so the phone stays paired. Sets logged by
Marrow 1.4 carry a set_type (work,
warmup, failure or drop). Warm-ups are still listed but no longer count toward
volume or records, and rows mirrored before the upgrade read as work sets.
Related MCP server: MetricBridge (formerly Health Export AI)
Connect an agent
The server speaks MCP over Streamable HTTP (JSON-RPC 2.0, protocol version
2025-06-18), authenticated with a bearer token it generates on first run and
prints alongside the pairing link.
Claude Code
claude mcp add --transport http marrow \
http://<server-ip>:8800/mcp \
--header "Authorization: Bearer <mcp token>"Claude Desktop, one click
Download marrow.mcpb,
double-click it, and Claude Desktop installs the extension and asks for the
URL and token. No terminal involved. (The bundle is a tiny zero-dependency
bridge in mcpb/. It forwards Claude's stdio to your Marrow URL and nothing
else.)
Claude Desktop (manual), Cursor, or anything using an mcp.json
{
"mcpServers": {
"marrow": {
"type": "http",
"url": "http://<server-ip>:8800/mcp",
"headers": { "Authorization": "Bearer <mcp token>" }
}
}
}Check it by hand
curl -s http://<server-ip>:8800/mcp \
-H "Authorization: Bearer <mcp token>" \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'Tools
Thirteen tools, all of them reads. The server also carries write tools (log a meal, a workout and so on), but it lists them only after a phone registers it for write-back, and today only Marrow Connect does that. A self-hosted server paired from the app serves the thirteen reads and nothing an agent can call writes to your health record.
Four of them answer in the app's own terms, scored against your own trailing normal with the same math the app's Home page uses (the day itself excluded), so an agent starts from a read that is already true for you instead of judging a number against the population:
Tool | Returns |
| One day: each key metric with its value and a phrase (normal for you, above your normal, well below your normal), food and water against your targets, last night's sleep, training done, mood and symptoms, and flags worth mentioning |
| Your own normal per metric: mean and spread over the window, the latest value's z and phrase, the 7-day mean and the 90-day trend per month |
| The recent days against the period before them: what moved and how notable it is for you, food, training, sleep and bedtime shifts, and streams that started or stopped arriving |
| What the mirror holds and how fresh it is: per metric the latest day, coverage, cadence, sources and whether it has gone stale, plus diary, sleep and training coverage and when the phone last synced |
The nine raw reads:
Tool | Returns |
| Recent days across activity, heart, sleep and nutrition |
| Every metric in the mirror, with units and coverage |
| Daily values for any metric, up to 400 days |
| Raw records with timestamps and source devices |
| Workouts from every source: activity, start, end, duration and source |
| The meal diary: every logged food with full nutrient detail, by day |
| Every lifting set with its set type and estimated 1RM, per-exercise progression, and volume per muscle group (warm-ups left out) |
| One night per wake day: bedtime, wake time, hours asleep, minutes per stage |
| Symptoms with their severity, and State of Mind entries with valence, feelings and what they were about |
Every read takes days back from the phone's today, or from and to on
the phone's calendar. metric_samples pages with before (the start of the
last record you have). Tools with an output schema also answer with
structuredContent.
Four prompts come with the server (how_am_i_doing, weekly_review,
doctor_prep, log_from_text) and four resources (marrow://today,
marrow://metrics, marrow://targets, marrow://quality), for the clients
that show them.
Metric keys: list_metrics shows Apple's short names (active_energy_burned),
and the tools also accept the app's own keys (active_energy,
heart_rate_variability), so an agent moved over from the phone keeps its
vocabulary.
Then ask your agent things like "how did my sleep change once I started training in the mornings?" and let it go and look.
Kits, recipes and the Claude Code plugin
kits/: copy-and-paste setup for Claude Code, Claude Desktop, Cursor, OpenClaw and Hermes Agent.
recipes/: receivers for Marrow's Automations (the app POSTs your data to any URL on a schedule, with the app closed): Home Assistant, n8n, Google Sheets through Apps Script, InfluxDB.
Built with Marrow: complete projects people run on these connections, starting with Body Ops, a Grafana dashboard for every kind of data Marrow sends. Submit yours there.
The Claude Code plugin:
/plugin marketplace add MarrowHealth/marrow-mcpthen/plugin install marrow-health@marrow. It adds the Marrow Connect server and four commands (/marrow-health:how-am-i-doing,weekly-review,doctor-prep,log) plus a skill that knows which tool answers what.
Why not the built-in Claude or ChatGPT connector?
Both Claude (Pro/Max, US) and ChatGPT now read Apple Health natively. Use them if that is all you need. They stop where this server starts:
Claude / ChatGPT connector | Marrow + this server | |
Where it works | The iOS app only | Claude Code, Claude Desktop, Cursor, OpenClaw, Hermes, any MCP client, on any machine |
When it works | While you are in the chat on the phone | 24/7, phone in your pocket, from your own box |
What the model sees | Raw HealthKit numbers | Daily values reconciled against Apple's own totals, meal diary, set-by-set lifts |
Where the data lives | Their cloud, per conversation | SQLite on hardware you own |
Cost | Subscription | Free, MIT |
OpenClaw / Hermes / any agent on a home machine. Point the agent's MCP
config at the server URL with the bearer token, exactly as in the mcp.json
block above. Reach it from outside the LAN with tailscale serve --bg --https=8800 http://127.0.0.1:8800 and use the tailnet URL.
The other ways in
This server is one of the doors on Marrow's Export tab, and you do not need it to give agents access:
Local MCP. Marrow runs an MCP server on the iPhone itself at
http://<phone-ip>:21212/mcp, answering while the app is running. Seven of the raw reads above, zero extra hardware.Server MCP. This package: an always-on mirror on your own box.
Automated. Scheduled pushes to any URL (Home Assistant, n8n, your own endpoint).
Manual. CSV, JSON and GPX files out of the share sheet.
All four are in the free tier. Setup for all of them: https://marrowhealthapp.com/guides.
Marrow Connect is the hosted Pro path: Marrow runs the mirror, and ChatGPT, Claude or Gemini read it with the phone asleep and nothing to run. It is the only door that can log for you, once you turn on Allow AI write in the app. https://marrowhealthapp.com/connect
Security
Both servers are built for a LAN or a tailnet. Do not port-forward this to the open internet. If you need it remotely, front it with
tailscale serve, Caddy, or an equivalent so the transport is HTTPS and the device is authenticated before the bearer token is ever presented.Two separate tokens live in
--data:.app-tokenfor the phone's pushes and.mcp-tokenfor agents. Rotating one does not disturb the other.Ingest is idempotent and UUID-keyed, so a replayed batch cannot double-count.
Status
Marrow is on the App Store, iOS 17+, and requires Apple Health. Get it on the App Store.
The iOS app is closed source. This server is not, because you should be able to read anything you are asked to run on your own hardware.
Registry
Listed in the official MCP registry
as tech.skeletonarmy/marrow, verified by DNS on skeletonarmy.tech.
mcp-name: tech.skeletonarmy/marrow
Help and policies
Agent setup guide, the full client-by-client walkthrough
Support and troubleshooting, or email support@skeletonarmy.tech
Privacy policy. Short version: your health data stays on your device, this server runs on hardware you own, and nothing here reports to us.
Licence
MIT. See LICENSE.
This server cannot be deployed
Maintenance
Related MCP Connectors
Your Apple Health data, food diary and lifts, for ChatGPT, Claude and Gemini. Approved on iPhone.
Your Garmin, Oura, WHOOP, Hevy and 35 more fitness apps, queryable from your own AI.
Read-only Apple Health data synced from your iPhone: sleep, heart rate, HRV, workouts and trends.
- freddyOAuthcoach.freddy
Connect your wearables, rings and training apps, then ask your AI about your own health data.
Related MCP Servers
- AlicenseAqualityBmaintenanceApple HealthKit → PostgreSQL sync + MCP server for Claude Code, Cursor, and Ollama. Open-source iOS app with reliable background sync (HKObserverQuery). 11 tools covering health summary, sleep, HRV trends, workouts, daily snapshots, metric stats, period comparison, and coaching briefs. Supports Supabase, Neon, and self-hosted Postgres. Privacy-first: your data goes to your own database.113MIT
- AlicenseAqualityAmaintenanceOpen-source MCP server for MetricBridge (formerly Health Export AI). 16 tools and 22 prompts let any MCP agent query 190 Apple Health metrics from files on your own machine. The server is read-only, has zero dependencies and makes zero network calls.16389 npm8MIT
- AlicenseAqualityAmaintenanceRead-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.927Apache 2.0
- AlicenseNot gradedqualityCmaintenanceProvides AI with read-only access to Apple Health data via three tools (health_now, health_detail, health_trends). Deployable on Cloudflare with a one-click mobile setup.1MIT