Yazio MCP
Enables querying Yazio food logs including meals, daily summaries, and nutrition totals through MCP tools.
README
Yazio MCP + Telegram Bot
A self-hosted nutrition assistant that exposes your Yazio food logs as an MCP server and a Telegram bot.
What's inside
| File | Purpose |
|---|---|
mcp_server.py |
FastMCP server — serves Yazio data over HTTP (Streamable HTTP transport) |
telegram_bot.py |
Telegram bot — answers nutrition questions via Groq + MCP tools |
render.yaml |
Render deployment config (single web service runs both) |
Architecture
Claude Desktop ──mcp-remote──▶ /mcp endpoint ──▶ Yazio API
▲
Telegram ──▶ Bot ──▶ Groq LLM ────┘
The MCP server and the Telegram bot run in the same Render process. The bot calls the MCP endpoint to fetch data rather than hitting the Yazio API directly.
MCP tools
| Tool | Description |
|---|---|
get_today_meals |
All meals logged today |
get_meals_for_date |
Meals for a specific date (YYYY-MM-DD) |
get_meals_for_range |
Meals over a date range |
get_daily_summary |
Daily calorie + macro totals for the last N days |
Deploy to Render
- Fork/clone this repo and push to GitHub.
- Create a new Web Service on render.com pointing to the repo.
- Build command:
pip install -r requirements.txt - Start command:
python mcp_server.py
- Build command:
- Set the following environment variables in the Render dashboard:
| Variable | Required | Description |
|---|---|---|
YAZIO_EMAIL |
✅ | Your Yazio account email |
YAZIO_PASSWORD |
✅ | Your Yazio account password |
TELEGRAM_BOT_TOKEN |
✅ | From @BotFather on Telegram |
GROQ_API_KEY |
✅ | Free at console.groq.com |
- Deploy. The MCP endpoint will be live at
https://<your-service>.onrender.com/mcp.
Connect to Claude Desktop
Add this to your claude_desktop_config.json:
{
"mcpServers": {
"yazio": {
"command": "npx",
"args": [
"mcp-remote",
"https://<your-service>.onrender.com/mcp"
]
}
}
}
Requires Node 20+. Install via nvm install 20 && nvm alias default 20.
Run locally
python -m venv .venv && source .venv/bin/activate
pip install -r requirements.txt
export YAZIO_EMAIL=you@example.com
export YAZIO_PASSWORD=yourpassword
python mcp_server.py
The server will start in stdio mode (for use with Claude Desktop directly).
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.