YazioSAFE
MCP server for managing Yazio user & nutrition data (unofficial)
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[!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": "[email protected]",
"YAZIO_PASSWORD": "your_password"
}
}
}
}Claude Desktop (Extension)
[!WARNING] One-click .mcpb install is broken by a Claude Desktop bug (mcpb#281). Workaround: download yazio-mcp.zip, extract it, and use **Se27b1aa5bf13aOBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add yazio-mcp --env YAZIO_USERNAME=${YAZIO_USERNAME} --env YAZIO_PASSWORD=${YAZIO_PASSWORD} -- npx -y [email protected]Exposed tools (15)
12 read · 2 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.
| Tool | Risk | Description |
|---|---|---|
add_user_consumed_item | write | |
add_user_water_intake | write | |
get_product | read | |
get_user | read | |
get_user_consumed_items | read | |
get_user_daily_summary | read | |
get_user_dietary_preferences | read | |
get_user_exercises | read | |
get_user_goals | read | |
get_user_settings | read | |
get_user_suggested_products | read | |
get_user_water_intake | read | |
get_user_weight | read | |
remove_user_consumed_item | destructive | |
search_products | read |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | WARN |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (4 observation(s))
- Network
- declared (1 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (3)
remove_user_consumed_item
.eslintrc.js
@anthropic-ai/mcpb, @modelcontextprotocol/sdk, @types/node, @typescript-eslint/eslint-plugin, @typescript-eslint/parser, esbuild, eslint, globals
Gates applied: no_behavioural_pass.
27b1aa5bf13afull audit observations/trust-audit/mcp-server/fliptheweb__yazio.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | 27b1aa5bf13a | SAFE | B | 89 | first audit |
Questions
What is the Yazio MCP server?
MCP server for managing Yazio user & nutrition data (unofficial)
What tools does Yazio expose?
15 in total: 12 read-only, 2 that write, and 1 that can delete or overwrite (remove_user_consumed_item). Every one is listed on this page with its risk.
Is Yazio safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B. Separately from the audit: 1 of its tools can destroy data, so scope the token you give it to what you actually need.
What credentials does Yazio need?
It reads YAZIO_PASSWORD and YAZIO_USERNAME from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Yazio run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as yazio-mcp at 0.0.14.
How current is this page?
The grade is for one exact copy of the source (27b1aa5bf13a), read on 2026-10-08. The repository is watched and re-audited when it changes.