adamwalt/myfitnesspal-mcp-python

开发工具

本页由 AI 翻译，技术细节请以原文为准。查看原文

70 stars 56 forks 质量 86 趋势 28MIT

Repository Install

adamwalt/myfitnesspal-mcp-python 是从 https://github.com/adamwalt/myfitnesspal-mcp-python. 导入的 MCP 服务器候选

概览

adamwalt/myfitnesspal-mcp-python 是从 https://github.com/adamwalt/myfitnesspal-mcp-python. 导入的 MCP 服务器候选

概述（AI 翻译）

一个模型上下文协议（MCP）服务器，使像Claude这样的AI助手能够与你的MyFitnessPal数据互动，包括饮食日记、锻炼、身体测量、营养目标和饮水量。

特色

工具	类型	描述
`mfp_get_diary`	阅读	获取任何日期的食物日记条目
`mfp_search_food`	阅读	搜索MyFitnessPal食品数据库
`mfp_get_food_details`	阅读	获取食品的详细营养信息
`mfp_add_food_to_diary`	写	在日记中添加一份特定餐食和日期的食物
`mfp_remove_food_from_diary`	写	删除你日记中的记录条目
`mfp_create_custom_food`	写	创建带有完整营养面板的私人定制食物
`mfp_list_own_foods`	阅读	列出你自己的自定义食物（私密食物不会出现在搜索中）
`mfp_delete_custom_food`	写	删除你自定义的食物
`mfp_get_measurements`	阅读	获取体重/身体测量历史
`mfp_set_measurement`	写入	记录新的体重或身体测量
`mfp_get_exercises`	阅读	获取记录的锻炼（有氧和力量）

本页由 AI 翻译，技术细节请以原文为准。

README

以下为原文 README 节选，完整内容请查看原文。

MyFitnessPal MCP Server

A Model Context Protocol (MCP) server that enables AI assistants like Claude to interact with your MyFitnessPal data, including food diary, exercises, body measurements, nutrition goals, and water intake.

Features

Tool	Type	Description
`mfp_get_diary`	Read	Get food diary entries for any date
`mfp_search_food`	Read	Search the MyFitnessPal food database
`mfp_get_food_details`	Read	Get detailed nutrition info for a food item
`mfp_add_food_to_diary`	Write	Add a food item to your diary for a specific meal and date
`mfp_remove_food_from_diary`	Write	Remove a logged entry from your diary
`mfp_create_custom_food`	Write	Create a private custom food with a full nutrition panel
`mfp_list_own_foods`	Read	List your own custom foods (private ones do not appear in search)
`mfp_delete_custom_food`	Write	Delete one of your custom foods
`mfp_get_measurements`	Read	Get weight/body measurement history
`mfp_set_measurement`	Write	Log a new weight or body measurement
`mfp_get_exercises`	Read	Get logged exercises (cardio & strength)
`mfp_get_goals`	Read	Get daily nutrition goals
`mfp_set_goals`	Write	Update daily nutrition goals
`mfp_get_water`	Read	Get water intake for a date
`mfp_set_water`	Write	Log water intake for a date
`mfp_get_steps`	Read	Get daily step counts synced from Apple Health / devices
`mfp_log_fast`	Write	Log a completed intermittent fasting window (start + end)
`mfp_update_fast`	Write	Update the start/end times of an existing fasting entry
`mfp_delete_fast`	Write	Delete a fasting entry by id
`mfp_get_report`	Read	Get nutrition reports over a date range
`refresh_browser_cookies`	Utility	Extract and save session cookies from browser

How diary writes work

MyFitnessPal has no public API. Reads here are scraped from the website via python-myfitnesspal, and diary writes go through MFP’s internal v2 JSON API — the same one their web client uses, authenticated with your existing session token.

Custom-food writes (mfp_create_custom_food, mfp_list_own_foods, mfp_delete_custom_food) use a different endpoint family: MFP’s v2 API exposes no custom-food create, so these call the same cookie-authenticated web endpoints their website uses (/api/auth/csrf, /api/services/users/foods/mine, /api/services/foods). No browser needs to be running — the stored session cookies are sufficient.

That interface is undocumented and was determined by observing the web client. It works today, but MyFitnessPal can change it without notice. They have already done so once: this server originally posted to /food/diary/{user}/add, which now returns 404, leaving food logging

在 GitHub 查看完整 README

安装

docker run -it --rm \

新手？先看 mcpskill.org 教程 →

配置

{
  "mcpServers": {
    "myfitnesspal": {
      "command": "/Users/yourname/myfitnesspal-mcp-python/venv/bin/python",
      "args": ["-m", "mfp_mcp.server"],
      "env": {
        "MFP_USERNAME": "gAAAAAB...<encrypted_email>",
        "MFP_PASSWORD": "gAAAAAB...<encrypted_password>"
      }
    }
  }
}