fitatu-wrapper
Enables programmatic access to Fitatu nutrition tracking via MCP tools for login, food search, product lookup, daily nutrition read, and adding entries.
README
Fitatu Wrapper
CLI and MCP wrapper for Fitatu.
Scope
This repository currently targets v1 of a product-only wrapper.
Included:
- programmatic login
- session refresh
- product search
- product details
- day read
- daily nutrition summary
- add product
- delete entry
Not included in v1:
- recipes
- water
- Own / Favorites / Fridge
- editing existing entries
Install
python3 -m pip install -e .
cp .env.example .env
Run
fitatu --help
Start the MCP server over stdio with:
fitatu-mcp
The CLI entrypoint is fitatu.
Implemented commands:
fitatu login --email ... --password ...fitatu whoamifitatu logoutfitatu search-food --date YYYY-MM-DD --meal breakfast --query bananafitatu get-product --product-id 105392008fitatu read-day --date YYYY-MM-DDfitatu read-day-summary --date YYYY-MM-DDfitatu read-days --from-date YYYY-MM-DD --to-date YYYY-MM-DDfitatu read-day-summaries --from-date YYYY-MM-DD --to-date YYYY-MM-DDfitatu add-product --date YYYY-MM-DD --meal breakfast --product-id ... --measure-id ... --quantity ...fitatu delete-entry --date YYYY-MM-DD --entry-id ...
All CLI output is JSON.
Read-oriented commands also support --out PATH for writing snapshots directly to disk.
The MCP entrypoint is fitatu-mcp.
Implemented tools:
fitatu_loginfitatu_whoamifitatu_logoutfitatu_search_foodfitatu_get_productfitatu_read_dayfitatu_read_day_summaryfitatu_add_productfitatu_delete_entry
The server uses FastMCP over stdio.
Automation Examples
Range exports for a dashboard:
fitatu read-days --from-date 2026-03-01 --to-date 2026-03-07 --out data/fitatu-days.json
fitatu read-day-summaries --from-date 2026-03-01 --to-date 2026-03-31 --out data/fitatu-summaries.json
Example cronjobs:
# macOS / BSD `date`
5 6 * * * cd /absolute/path/to/fitatu-wrapper && /absolute/path/to/.venv/bin/fitatu read-day --date $(date +\%F) --out data/today.json
10 6 * * * cd /absolute/path/to/fitatu-wrapper && /absolute/path/to/.venv/bin/fitatu read-day-summaries --from-date $(date -v-6d +\%F) --to-date $(date +\%F) --out data/weekly-summaries.json
Linux / GNU date variant:
10 6 * * * cd /absolute/path/to/fitatu-wrapper && /absolute/path/to/.venv/bin/fitatu read-day-summaries --from-date $(date -d '6 days ago' +\%F) --to-date $(date +\%F) --out data/weekly-summaries.json
For dashboard ingestion, prefer the CLI over MCP and persist JSON snapshots locally.
Configuration
Copy .env.example to .env for local development.
The runtime loads .env automatically.
Important rules:
- never commit a real
.env - never put real credentials or tokens into
.env.example - treat
.env.exampleas documentation, not as a secrets file
Supported environment variables:
FITATU_API_BASE_URLFITATU_SESSION_PATHFITATU_USERNAMEFITATU_PASSWORDFITATU_API_KEYFITATU_API_SECRETFITATU_LOGIN_API_CLUSTERFITATU_APP_LOCATION_COUNTRYFITATU_APP_UUIDFITATU_APP_VERSIONFITATU_APP_LOCALEFITATU_APP_SEARCHLOCALEFITATU_APP_STORAGELOCALEFITATU_APP_TIMEZONEFITATU_APP_OS
Zero-Bootstrap Login
The default path is now browserless and zero-bootstrap:
fitatu login --email ... --password ...can work with only credentials- the client fetches the public Fitatu login page and web bundle
- it extracts the public web-app config needed for the first login request
- after login, the session file stores the user tokens and user-scoped headers for normal reuse
This means:
- browser automation is not required for normal CLI or MCP use
- manual
FITATU_API_*/FITATU_APP_*values are not required for first login - those header env vars are now advanced debug or override inputs, not mandatory setup
The repository does not include real values for any of these fields. Populate them from your own local setup only.
Live Smoke
The repo includes opt-in live smoke tests for zero-bootstrap browserless operation.
By default they are skipped. To run them:
FITATU_RUN_LIVE=1 python3 -m pytest -m live tests/test_live_smoke.py
Required live-smoke inputs:
FITATU_USERNAMEFITATU_PASSWORDFITATU_LIVE_DATE- optionally
FITATU_LIVE_MEALandFITATU_LIVE_QUERY
Optional write smoke inputs:
FITATU_LIVE_PRODUCT_IDFITATU_LIVE_MEASURE_IDFITATU_LIVE_QUANTITY
The live smoke tests unset all manual FITATU_API_* and FITATU_APP_* env vars before building the client config. They then perform programmatic login and run the v1 read and write flows. That proves the browserless path works without manual bootstrap configuration.
Development
The project uses:
- Python 3.12+
typerfor the CLIpydanticfor public modelsmcpfor the MCP serverpytestfor testsrufffor linting
Checks:
ruff check .
python3 -m pytest
If you are changing CLI or MCP behavior, update this README in the same change.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.