Show HN: Apple Health MCP Server

#1

Post by _neil » Wed, Jul 23, 2025, 5:23 PM UTC

Hey HN,

This is an MCP server to chat with Apple Health data. I built it because I'm working on (yet another) personal trainer tool that keeps track of my workout goals, etc. and does scheduling for me. Part of that is weekly check-ins. I thought pairing those check-ins with sensor data could be useful, so here we are.

It seems there isn't a way to automate access to Apple Health data, so this relies on an iOS app that can quickly/easily export key data to CSV. So the process at the moment is to export the data every Sunday before doing a check-in. More steps than I'd like, but in practice isn't a big lift.

Under the hood this is mostly a thin wrapper around duckdb.

There's a video of it in action here: https://x.com/realtron/status/1947710791521591514

Show HN: Apple Health MCP Server
github.com

Re: Show HN: Apple Health MCP Server

#2

Post by brandonb » Fri, Jul 25, 2025, 12:50 PM UTC

Super cool. An iPhone + Apple Watch generate about 40 distinct biomarkers of your data (resting heart rate, VO2max, workouts, sleep stages, sleep apnea risk, ECGs, and so on), but the ability to interpret them is very limited.

I work on an iOS health app, and I'd love to try integrating this. It'd help eliminate the step of having to manually export to a CSV every Sunday.

Feel free to shoot me an email if you want to collaborate!

Re: Show HN: Apple Health MCP Server

#3

Post by monatron » Fri, Jul 25, 2025, 1:00 PM UTC

Very cool indeed. I started building something similar - relying on Auto Export [https://apps.apple.com/us/app/health-auto-export-json-csv/id...] to export my health data to an endpoint which stores it in a sqlite database. I never got as far as building an MCP server around the data but that's certainly the direction I was heading. The initial idea was to use my health data to provide context to a health/fitness agent that would recommend workouts, check-in on things, etc.

Re: Show HN: Apple Health MCP Server

#4

Post by guzik » Fri, Jul 25, 2025, 1:00 PM UTC

brandonb wrote: post #2

Super cool. An iPhone + Apple Watch generate about 40 distinct biomarkers of your data (resting heart rate, VO2max, workouts, sleep stages, sleep apnea risk, ECGs, and so on), but the ability to interpret them is very limited. I work on an iOS health app, and I'd love to try integrating this. It'd help eliminate the step of having to manually export to a CSV every Sunday. Feel free to shoot me an email if you want to…

we've built a wrapper around Apple Health to simplify data extraction and synchronization. If you think this might be useful, feel free to drop me a message.

Re: Show HN: Apple Health MCP Server

#5

Post by dkdcio » Fri, Jul 25, 2025, 1:33 PM UTC

monatron wrote: post #3

Very cool indeed. I started building something similar - relying on Auto Export [ https://apps.apple.com/us/app/health-auto-export-json-csv/id... ] to export my health data to an endpoint which stores it in a sqlite database. I never got as far as building an MCP server around the data but that's certainly the direction I was heading. The initial idea was to use my health data to provide context to a health/fitness a…

it is wild to me that products like this don’t allow you to easily export all data into sqlite (or duckdb) natively. it’s 2025 and you frequently have to page through hundreds or thousands of API calls to get a trivial amount of data (or use 3p services)

Re: Show HN: Apple Health MCP Server

#6

Post by friggeri » Fri, Jul 25, 2025, 1:43 PM UTC

This is awesome! I’ve been working on and off for the last few months on an AI running coach app. Would love to compare notes of effectively prompting Claude or O3 to analyze workouts / build workout plans. In my experience it still requires a lot of hand holding (sudden mileage increases w/w, inconsistent intervals, etc)

Re: Show HN: Apple Health MCP Server

#7

Post by formerly_proven » Fri, Jul 25, 2025, 1:50 PM UTC

There is a native export function in Health but it generates about 1-2 GB of XML per year, since the schema is extremely verbose, so it takes a while. On the other hand, it’s very literally self-describing. But no need for handing access to Health to more or less dubious apps. I also think you can „export“ select data points to „CSV“ using a ten step Shortcut. Might be quicker.

Re: Show HN: Apple Health MCP Server

#8

Post by dostick » Fri, Jul 25, 2025, 1:51 PM UTC

What Apple health actually is? It’s Apple Watch. My data coming from Oura and Withings, I wonder maybe those would have better ways to integrate with actual API.

Re: Show HN: Apple Health MCP Server

#9

Post by rikbruggink » Fri, Jul 25, 2025, 1:54 PM UTC

friggeri wrote: post #6

This is awesome! I’ve been working on and off for the last few months on an AI running coach app. Would love to compare notes of effectively prompting Claude or O3 to analyze workouts / build workout plans. In my experience it still requires a lot of hand holding (sudden mileage increases w/w, inconsistent intervals, etc)

i am trying todo same with glue-ing mcp servers together and as a bonus try get my CHO rates and overall KCAL for the week with the proposed schedule and all palnned intake based on mets. Analyzing my workouts is something that works great at the moment if the data in is correct. i mostly use intervals.icu for this.

Would love to chip in on the discussion around this topic.

Re: Show HN: Apple Health MCP Server

#10

Post by yurishimo » Fri, Jul 25, 2025, 1:59 PM UTC

monatron wrote: post #3

Very cool indeed. I started building something similar - relying on Auto Export [ https://apps.apple.com/us/app/health-auto-export-json-csv/id... ] to export my health data to an endpoint which stores it in a sqlite database. I never got as far as building an MCP server around the data but that's certainly the direction I was heading. The initial idea was to use my health data to provide context to a health/fitness a…

Thanks for the link to that app. Gonna setup something this weekend to ingest and aggregate my workout stats onto my personal website :)