MyFitnessPal MCP Server

MyFitnessPal MCP Server

Enables AI assistants to read and log MyFitnessPal nutrition data, including tracking calories, macros, searching foods, and adding meals through natural conversation.

Category
访问服务器

README

MyFitnessPal MCP Server

An MCP server that lets AI assistants read and log your MyFitnessPal nutrition data. Track calories, macros, search foods, and add meals — all through natural conversation.

Tools

Tool Description
get_diary Get food diary entries for a specific date
get_nutrition_summary Get calories and macros summary for a date
get_goals Get your daily calorie and macro targets
quick_add_calories Quick-add calories (and optionally macros) to a meal
search_food Search the MFP food database
get_food_details Get nutrition info and serving sizes for a food item
add_food Log a food item to your diary

Setup

1. Get your session cookie

MyFitnessPal doesn't have a public API, so this server authenticates using your browser's session cookie.

  1. Log into MyFitnessPal in your browser
  2. Open DevTools (F12 or Cmd+Option+I)
  3. Go to Application → Cookies → www.myfitnesspal.com
  4. Copy the full cookie string (or use the helper script below)

Or use the helper script:

npm run export-cookies

2. Configure environment

cp env.example .env

Fill in your values:

MFP_SESSION_COOKIE=your_session_cookie_value_here
MFP_USERNAME=your_username

3. Build

npm install
npm run build

Usage

Claude Code

Add to ~/.claude/settings.json:

{
  "mcpServers": {
    "myfitnesspal": {
      "type": "stdio",
      "command": "node",
      "args": ["/path/to/myfitnesspal-mcp/dist/index.js"]
    }
  }
}

Cursor

Add to .cursor/mcp.json:

{
  "mcpServers": {
    "myfitnesspal": {
      "type": "stdio",
      "command": "node",
      "args": ["/path/to/myfitnesspal-mcp/dist/index.js"]
    }
  }
}

Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS):

{
  "mcpServers": {
    "myfitnesspal": {
      "type": "stdio",
      "command": "node",
      "args": ["/path/to/myfitnesspal-mcp/dist/index.js"]
    }
  }
}

Replace /path/to/myfitnesspal-mcp with the actual path to this repo.

Remote Deployment (Cloudflare Workers)

The worker/ directory contains a Cloudflare Workers deployment for using this as a remote MCP server.

cd worker
npm install
npx wrangler login
npx wrangler deploy
npx wrangler secret put MFP_SESSION_COOKIE   # paste your cookie when prompted

Then connect from Claude Desktop:

{
  "mcpServers": {
    "myfitnesspal": {
      "command": "npx",
      "args": ["mcp-remote", "https://myfitnesspal-mcp.<your-subdomain>.workers.dev/mcp"]
    }
  }
}

Session Expiration

MFP session cookies expire roughly every 30 days. If you get auth errors, grab a fresh cookie from your browser and update your .env (or run npx wrangler secret put MFP_SESSION_COOKIE for the worker).

License

MIT

Disclaimer

Unofficial integration for personal use. Please respect MyFitnessPal's Terms of Service.

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选