Fitatu Nutrition MCP Server
Syncs and retrieves daily nutrition data (meals and macros) from Fitatu via MCP tools, with SQLite caching and HTTP Streamable transport.
README
Fitatu Nutrition MCP Server (FastAPI)
This server exposes daily nutrition data (meals and macros) through MCP HTTP Streamable transport. SQLite is used as a cache layer. Sync is additive: only new meal items are inserted; existing cached items are preserved.
Endpoints
GET /health- MCP Streamable HTTP endpoint:
/mcp
MCP tools (HTTP Streamable)
sync_day(day_date)get_day_summary(day_date)get_day_macros(day_date)get_day_meals(day_date)get_cache_stats(day_date)
sync_day also returns:
cache_delta: newly added meals/items in this sync runcache_totals: total cached meals/items for that day
Parameter format: day_date = "YYYY-MM-DD"
Local run
Set credentials:
FITATU_USERNAMEFITATU_PASSWORDFITATU_API_SECRET— can be obtained by inspecting network requests in the Fitatu web app (e.g. via browser DevTools); look for theapi-secret(or similar) header in authenticated API calls
Then run:
PowerShell:
pip install -r mcp_server/requirements.txt
$env:FITATU_USERNAME="your_email"
$env:FITATU_PASSWORD="your_password"
$env:FITATU_API_SECRET="your_api_secret"
python -m uvicorn mcp_server.server:app --host 0.0.0.0 --port 8000
bash/zsh:
pip install -r mcp_server/requirements.txt
export FITATU_USERNAME="your_email"
export FITATU_PASSWORD="your_password"
export FITATU_API_SECRET="your_api_secret"
python -m uvicorn mcp_server.server:app --host 0.0.0.0 --port 8000
Docker
Build image:
docker build -t fitatu-mcp-server ./mcp_server
Run container (username/password passed at runtime):
docker run --rm -p 8000:8000 \
-e FITATU_USERNAME="your_email" \
-e FITATU_PASSWORD="your_password" \
-e FITATU_API_SECRET="your_api_secret" \
-e FITATU_DB_FILE="/data/fitatu_nutrition.db" \
-v "${PWD}/data:/data" \
fitatu-mcp-server
Use MCP tool sync_day first, then read data with the remaining tools.
n8n MCP integration
Configure MCP client in n8n to use HTTP Streamable transport with URL:
http://<host>:8000/mcp/
Use MCP tools listed above directly in n8n flows.
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.