io.github.fliptheweb/yazio-mcp MCP Server
io.github.fliptheweb/yazio-mcp
Connect Claude/Cursor to your Yazio nutrition data—track diet, search foods, and manage goals.
What is the io.github.fliptheweb/yazio-mcp MCP server?
The Yazio MCP server connects Claude and Cursor to your Yazio nutrition account using an unofficial reverse-engineered API. It enables you to retrieve diet summaries, search food products, log meals, track exercises and weight, and manage nutrition goals directly from your AI assistant.
This server bridges your Yazio nutrition app to Claude and Cursor, letting you analyze eating patterns, search the Yazio food database, add forgotten meals, and review your fitness data without leaving your AI chat. It uses an unofficial API, so functionality may change if Yazio updates their backend.
How to install io.github.fliptheweb/yazio-mcp
Copy-paste configuration for popular MCP clients.
YAZIO_USERNAMErequiredsecretYazio Username
YAZIO_PASSWORDrequiredsecretYazio Password
Tools & capabilities
Tools this server exposes to the agent.
get_user_daily_summary— Get daily nutrition summary for a specified dateget_user_consumed_items— Get food entries logged for a specific dateget_user_weight— Get weight data and historyget_user_exercises— Get exercise data for a specified dateget_user_water_intake— Get water intake data for a specified dateget_user_goals— Get nutrition goalsget_user_settings— Get user preferences and settingssearch_products— Search Yazio's food database by queryget_product— Get detailed nutritional information for a specific productadd_user_consumed_item— Add a food entry to your log with product ID, amount, date, and meal typeadd_user_water_intake— Add water intake entry (cumulative value in ml) for a dateremove_user_consumed_item— Remove a food entry from your log
Use cases
- Analyze your nutrition trends and eating patterns over time by retrieving daily summaries and identifying macro distribution issues
- Search the Yazio food database to find detailed nutritional information for any food product including calories, macros, vitamins, and minerals
- Log meals you forgot to track in the Yazio app directly from Claude or Cursor with specific amounts and meal types
- Review your exercise history and water intake to get a complete picture of your health and fitness activities
- Monitor your weight trends and compare against your nutrition goals to track progress
io.github.fliptheweb/yazio-mcp MCP server FAQ
It's an unofficial MCP server that connects Claude and Cursor to your Yazio nutrition account, allowing you to access diet data, search foods, log meals, and track fitness metrics from your AI assistant.
No, this is an unofficial server using a reverse-engineered API. Yazio does not provide an official API, and the server may stop working if Yazio changes their backend.
Add the server to your claude_desktop_config.json with the npx command and your Yazio credentials as environment variables. One-click .mcpb install is currently broken; use the manual JSON config or the unpacked extension workaround instead.
Use Settings → MCP → Add new MCP server and enter the command (npx), args (-y yazio-mcp), and environment variables (YAZIO_USERNAME and YAZIO_PASSWORD), or add the config to .cursor/mcp.json in your project.
Yes, the server itself is free (MIT licensed). You need a valid Yazio account to use it, which has its own pricing model.
Your Yazio email and password, passed as YAZIO_USERNAME and YAZIO_PASSWORD environment variables. Credentials are only used to authenticate with Yazio's servers.
README (reference)
Source of truth, from the repository.
Yazio MCP Server <img src="https://assets.yazio.com/frontend/images/branded-logo-dark.svg" alt="Yazio Logo" width="104" height="28" />
[!IMPORTANT] This is not an official MCP server and Yazio does not provide an official API. This server uses an unofficial reverse-engineered API and may stop working at any time.
An MCP (Model Context Protocol) server that connects Claude/Cursor to your Yazio nutrition data. Track your diet, search food products, and manage your nutrition goals directly from your AI assistant.
Available on NPM: npx yazio-mcp
Claude Desktop Extension: yazio-mcp.mcpb — one-click install is broken upstream, see workaround.
✨ Features
- 🔐 Authentication - Connect with your Yazio account
- 📊 Nutrition Analysis - Get comprehensive diet data and insights
- 🍎 Food Tracking - Search, add, and manage food entries
- 🏃♂️ Fitness Data - Track exercises and water intake
- ⚖️ Weight Monitoring - View weight history and trends
- 🎯 Goal Management - Access and manage nutrition goals
- 🔍 Product Search - Search Yazio's extensive food database
🚀 Quick Start
Add the following JSON your MCP client configuration:
{
"mcpServers": {
"yazio": {
"command": "npx",
"args": ["-y", "yazio-mcp"],
"env": {
"YAZIO_USERNAME": "your_email@emai.com",
"YAZIO_PASSWORD": "your_password"
}
}
}
}
Claude Desktop (Extension)
[!WARNING] One-click
.mcpbinstall is broken by a Claude Desktop bug (mcpb#281). Workaround: download yazio-mcp.zip, extract it, and use Settings → Extensions → Advanced settings → Install Unpacked Extension. Or just use thenpxconfig above.
Claude Desktop (Manual)
~/Library/Application Support/Claude/claude_desktop_config.json
Claude Code (CLI)
claude mcp add yazio -e YAZIO_USERNAME=your_email@email.com -e YAZIO_PASSWORD=your_password -- npx -y yazio-mcp
Verify with claude mcp list.
Cursor
There are a few ways to add the server:
- Settings UI (easiest) —
Settings → MCP → + Add new MCP server, then fill in the command, args, and env - Project config — add JSON to
.cursor/mcp.jsonin your project root - Global config — add JSON to
~/.cursor/mcp.json(applies to all projects)
💡 Use Cases
📈 Analyze Your Nutrition Trends
"Get my nutrition data for the last week and analyze my eating patterns"
Claude can retrieve your daily summaries, identify trends, and provide insights about your eating habits, macro distribution, and areas for improvement.
🔍 Search Food Products
"Search for 'chicken breast' in the Yazio database"
Find detailed nutritional information for any food product, including calories, macros, vitamins, and minerals.
📝 Add Forgotten Meals
"Add 200g of grilled salmon for yesterday's dinner"
Easily log meals you forgot to track in the Yazio app directly from Claude or Cursor.
🛠️ Available Tools
| Tool | Description | Key Parameters |
|---|---|---|
get_user_daily_summary | Get daily nutrition summary | date |
get_user_consumed_items | Get food entries for a date | date |
get_user_weight | Get weight data | - |
get_user_exercises | Get exercise data | date |
get_user_water_intake | Get water intake | date |
get_user_goals | Get nutrition goals | - |
get_user_settings | Get user preferences | - |
search_products | Search food database | query |
get_product | Get detailed product info | id |
add_user_consumed_item | Add food to your log | productId, amount, date, mealType |
add_user_water_intake | Add water intake entry (cumulative value in ml) | date, water_intake |
remove_user_consumed_item | Remove food from log | itemId |
Test Connection
YAZIO_USERNAME='your_email' YAZIO_PASSWORD='your_password' npx yazio-mcp
⚠️ Important Disclaimers
- Unofficial API: This uses a reverse-engineered API that may break
- Credentials: Your Yazio credentials are only used for auth on Yazio servers
- Use at Your Own Risk: API changes could affect functionality
📋 Requirements
- Node.js 18+ (for npx)
- Valid Yazio account
- MCP-compatible client (Claude Desktop, Cursor, etc.)
Development
- Download the repository
- Point to local copy in your mcp config
- Debugging:
YAZIO_USERNAME=X YAZIO_PASSWORD=X npx -y @modelcontextprotocol/inspector npx <local-path>/yazio-mcp
📄 License
MIT License - see LICENSE file for details.
Related MCP servers
MCP server for FatSecret API - food search, nutrition, diary, recipes, weight tracking (unofficial)

OpenBoss
Public internet HP bar. Agents smack it over MCP. They cannot complete payment.
Source-linked enterprise AI deployment search. Free preview; API keys unlock full results.

PassNinja
Issue and manage Apple Wallet & Google Wallet passes from any MCP-aware AI client.

io.github.floomhq/floom
Deploy Python functions as background AI workers with scheduling, approvals, logs, REST API, and MCP access.
Zero-auth chat and durable notes for AI agents over plain HTTP—rendezvous, hand-off, and coordination.

