Mirobody
Lab results to LOINC codes and UCUM units, symptoms and diagnoses to ICPC-3. Offline, no API key.
作者提供的说明(英文原文)
MCP server for accessing Yazio user & nutrition data (unofficial)
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
YAZIO_USERNAME, YAZIO_PASSWORD标为机密的值是你账户的钥匙。千万不要分享给别人,也不要粘贴到聊天里。
你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"yazio": {
"command": "npx",
"args": [
"-y",
"yazio-mcp"
],
"env": {
"YAZIO_USERNAME": "your-value",
"YAZIO_PASSWORD": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add yazio --env YAZIO_USERNAME=your-value --env YAZIO_PASSWORD=your-value -- npx -y yazio-mcp运行前请先填写空着的值。
粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"yazio": {
"command": "npx",
"args": [
"-y",
"yazio-mcp"
],
"env": {
"YAZIO_USERNAME": "your-value",
"YAZIO_PASSWORD": "your-value"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"yazio": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"yazio-mcp"
],
"env": {
"YAZIO_USERNAME": "your-value",
"YAZIO_PASSWORD": "your-value"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。
你的选择通过 Cookie 保存在这台设备上,无需账户。
这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月7日
注册名称已通过 GitHub 账户 fliptheweb 验证,该账户拥有此仓库
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
它在你的电脑上运行;我们只能读取互联网端点的工具列表
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
你需要填写:YAZIO_USERNAME, YAZIO_PASSWORD
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
GitHub 仓库最后更新于–,最新版本(0.0.15)于15天前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Node.js。
同一分类中有:Mirobody, FHIR MCP Server, Google Health MCP
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Lab results to LOINC codes and UCUM units, symptoms and diagnoses to ICPC-3. Offline, no API key.
MCP server providing seamless access to FHIR APIs for AI tools and healthcare applications
Privacy-first unofficial Google Health API v4 MCP server for health, sleep, activity, HR agents
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
[!IMPORTANT]
This is not an official MCP server and Yazio does not provide an official API.
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.
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" } } } }
[!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.
~/Library/Application Support/Claude/claude_desktop_config.json
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.
There are a few ways to add the server:
Settings → MCP → + Add new MCP server, then fill in the command, args, and env.cursor/mcp.json in your project root~/.cursor/mcp.json (applies to all projects)*"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 for 'chicken breast' in the Yazio database"*
Find detailed nutritional information for any food product, including calories, macros, vitamins, and minerals.
*"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.
| Tool | Description | Key Parameters |
|---|---|---|
get_user | Get user profile | - |
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 | date (optional) |
get_user_exercises | Get exercise data | date |
get_user_water_intake | Get water intake | date |
get_user_goals | Get nutrition goals | date (optional) |
get_user_settings | Get user preferences | - |
get_user_dietary_preferences | Get dietary preferences | - |
get_user_suggested_products | Get suggested products for a meal | date, daytime, limit (all optional) |
search_products | Search food database | query |
get_product | Get detailed product info | id |
get_recipe | Get a recipe with ingredients and nutrients | id |
get_user_recipes | Get your own recipes | - |
delete_user_recipe | Delete one of your own recipes | id |
add_user_consumed_item | Add food to your log | product_id, amount, date, daytime |
add_user_water_intake | Add water intake entry (cumulative value in ml) | date, water_intake |
remove_user_consumed_item | Remove food from log | itemId |
create_product | Create a custom product from label values per 100 g/ml | name, category, energy_per_100, protein_per_100, fat_per_100, carb_per_100 |
add_quick_entry | Log a one-off entry with total nutrition, without a product ("quick add") | name, date, daytime, energy |
add_user_consumed_recipe | Log portions of a recipe | recipe_id, portion_count, date, daytime |
YAZIO_USERNAME='your_email' YAZIO_PASSWORD='your_password' npx yazio-mcp
YAZIO_USERNAME=X YAZIO_PASSWORD=X npx -y @modelcontextprotocol/inspector npx <local-path>/yazio-mcp
MIT License - see LICENSE file for details.