Building an MCP Server to Let Claude Read My Blood Sugar
I started wearing a continuous glucose monitor, and within weeks I'd accumulated over 150,000 data points.
The data was interesting. The problem was accessing it. I wanted to actually interrogate my data - correlate glucose spikes with meals, compare patterns across weeks, ask questions I hadn't thought of yet.
So I built an MCP server that lets Claude query my blood sugar directly. Now I can ask "what was my average reading last week?" or "when do I typically see spikes?" and get real answers from my own data.
The code is open source and surprisingly simple - about 100 lines of Python.
Withings MCPNew!!
Talking to My Scales: A Withings MCP Server I've been building a small collection of personal MCP (Model Context Protocol) servers that let an AI assistant like Claude pull data from the services I actually use — Strava, Spotify, Garmin, and my Withings body scale. This post covers the Withings one: how it authenticates, what it exposes, […]
Straify - Strava meets SpotifyNew!!
It started with a simple question: Which Spotify tracks make me run faster? As a runner who always trains with music, I thought I picked up the pace and pushed on during certain songs. That curiosity led me to build Straify, a project that began as a way to correlate my Spotify listening history with my Strava […]