Mi Fitness MCP
MCP server for Mi Fitness cloud data. Provides a local SQLite-backed server to sync and query daily activity, heart rate, and body measurements.
README
Mi Fitness MCP
MCP server for Mi Fitness data.
This project provides a local SQLite-backed MCP server for Mi Fitness cloud data.
Current data coverage
Confirmed with the current cloud flow:
- daily activity
- steps
- distance
- active calories
- heart rate
- body measurements
- weight
- BMI
- fat, water, bone, and muscle metrics
- visceral fat
- basal metabolism
Not yet confirmed with the current Xiaomi cloud endpoint:
- sleep
- workouts
Install
python -m venv .venv
source .venv/bin/activate
pip install -e '.[dev]'
Setup
You need:
userIdpassToken
Typical flow:
- Open
https://account.xiaomi.com - Sign in to your Xiaomi account
- Open browser DevTools
- Inspect cookies for
account.xiaomi.com - Copy
userIdandpassToken
Configure the server:
mi-fitness-mcp setup --mode mi_fitness_cloud --user-id "<userId>" --pass-token "<passToken>" --region ru
mi-fitness-mcp doctor
For local endpoint exploration there is also a probe script:
python probe_mifitness.py --user-id "<userId>" --pass-token "<passToken>"
Use
mi-fitness-mcp sync --start-date 2025-04-01 --end-date 2025-05-31
mi-fitness-mcp serve
MCP client config
Example Claude Desktop config:
{
"mcpServers": {
"mi-fitness": {
"command": "mi-fitness-mcp",
"args": ["serve"]
}
}
}
Example prompts
Show my daily activity for the last 14 daysHow has my resting heart rate changed this month?Summarize my latest body measurementsSync my latest Mi Fitness data
Commands
mi-fitness-mcp --help
mi-fitness-mcp setup --help
mi-fitness-mcp doctor
mi-fitness-mcp sync --help
mi-fitness-mcp serve
Development
pytest
python -m build
Troubleshooting
Connection: failed- verify
userIdandpassToken - verify region, usually
ru
- verify
Credentials not found- run
setupagain
- run
syncreturns no data- try another date range
- verify that the data actually exists in Mi Fitness cloud
Security
passTokenis stored via the system keyring- do not commit
.env, local config files, or real credentials - rotate tokens if they were pasted into chats or shell history
Disclaimer
This is an unofficial project and is not affiliated with Xiaomi.
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。