About Olympus
Olympus is an MCP server published by rohnach29 in the AI category: a terminal you can drive from code: create, drive, observe and tear down real terminal sessions on zmx, tmux, meja or herdr, through a Go package, a CLI and a stdio MCP server.
The repository has 1 stars and 0 forks, with the last commit 8 months ago. Six months or more without a commit doesn't mean the server is broken, but check the open issues before depending on it in production.
Install
git clone https://github.com/rohnach29/olympusThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Ask AI
Ask AI about Olympus
Powered by Claude · Grounded in docs
Security checks
- ✓README presentThe repository ships documentation.
- !Scoped permissionsDoesn't declare a permission scope. Assume it can do anything its process can.
4 checks have not been run yet.
README
Olympus
An AI-powered health platform that gives LLMs real-time access to your biometrics through a custom MCP server. Deployed on Vercel, syncs with Apple Watch.
Why This Exists
Most health apps show you dashboards. Olympus lets you talk to your health data. Ask "Why am I tired today?" and the AI pulls your sleep stages, HRV, and recovery scores to give you a real answer.
How It Works
Claude (or any LLM)
↓ MCP Protocol
MCP Server → exposes tools like get_sleep_data, log_food, get_hrv_trend
↓ REST
Next.js API routes → health data, USDA nutrition search, LLM client
↓ Drizzle ORM
PostgreSQL
The MCP server is the interesting part — it lets Claude autonomously query and log health data without copy-pasting. You just talk to it.
What I Built
MCP Server (/mcp-server)
Custom Model Context Protocol server exposing 27 tools: health summaries, sleep analysis, HRV trends, workout logs, food logging, USDA search, blood work, and longevity metrics.
Apple Watch Integration
Syncs real biometric data — sleep stages, HRV, workouts, recovery — from HealthKit.
RAG for Food Logging
"I had a chicken burrito" → USDA database search → structured macro/micronutrient JSON. No manual entry.
Pluggable LLM Backend
Local inference with Ollama/DeepSeek for privacy, or Groq API for speed. One env var to switch.
Stack
- Next.js 16 / React 19 / TypeScript / Tailwind
- PostgreSQL + Drizzle ORM
- MCP server with @modelcontextprotocol/sdk
- Apple HealthKit integration
- Ollama or Groq for LLM
- Deployed on Vercel
Running Locally
npm install
# Postgres
docker run --name olympus-db -e POSTGRES_DB=olympus -e POSTGRES_PASSWORD=password -p 5432:5432 -d postgres:16
cp .env.example .env.local
npm run db:push
npm run dev
Using the MCP Server with Claude
Build the MCP server:
cd mcp-server && npm install && npm run build
Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"olympus": {
"command": "node",
"args": ["/path/to/olympus/mcp-server/dist/index.js"]
}
}
}
Restart Claude Desktop. You can now ask Claude things like "How did I sleep last night?" or "Log that I had a chicken burrito for lunch" and it will query/update your health data directly.
License
MIT
README copy captured when this server was indexed; it may lag the repository. The original is authoritative.