Claude Fit Logger
Description
Log food to Google Health by talking to Claude — automatic nutrition lookup via USDA/Open Food Facts, an MCP server on Render, Neon Postgres for entry tracking, and a custom OAuth 2.1 shim for Claude's connector requirement.
Installation
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open the source below and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
README
Claude Fit Logger
Log food and drink to Google Health by just talking to Claude — from your phone, no manual entry. Claude looks up nutrition automatically (USDA / Open Food Facts, falling back to its own estimate when nothing matches), writes it to Google Health, and keeps a running daily table in chat with support for undo and corrections.
How it works
You (phone) → Claude (chat + skill) → MCP server (Render)
├─ Nutrition lookup (USDA / Open Food Facts)
├─ Entry log (Neon Postgres) — powers undo/remove
└─ Google Health API — the actual food log
Full breakdown, including a diagram, in [`docs/architecture.pdf`](docs/architecture.pdf).
Status
Working end-to-end: logging, automatic nutrition lookup with manual fallback, undo, remove, and running totals all sync correctly to the Google Health app. Single-user by design — see [`docs/security.pdf`](docs/security.pdf) for why that matters before extending this to anyone else.
Repository structure
claude-fit-logger/
├── docs/ # Full documentation (see below)
├── server/ # Deployable MCP server (Render root directory)
│ ├── main.py # Tool definitions + auth
│ ├── db.py # Neon-backed entry log
│ ├── health_client.py # Google Health API client
│ ├── nutrition_lookup.py
│ ├── oauth.py # OAuth 2.1 shim for Claude's connector requirement
│ └── requirements.txt
├── PRIVACY.md # Required for Google OAuth production publishing
└── .gitignore
Documentation
| Document | Covers |
|---|---|
| `docs/install.pdf` | Full setup from scratch: Google Cloud, Neon, Render, Claude connector |
| `docs/architecture.pdf` | System design, data flow, component breakdown |
| `docs/api_reference.pdf` | The four MCP tools: parameters and response s |
Related Skills
mcp-server-postgres
Read-only PostgreSQL database access.
Data mcp-server-sqlite
SQLite database interaction and querying.
Data mcp-server-google-maps
Google Maps integration for location data.
Data Bitbucket Data Center
---
Data Private Gpt
Complete API layer for private AI applications on local models: RAG, skills, tools, MCP, text-to-sql, and more
Data Csv Data Summarizer
Automatically analyze CSV files and generate comprehensive insights with visualizations
Data