个人 MCP 服务器
用于个人健康和幸福感追踪的模型上下文协议服务器。该服务器提供用于追踪锻炼、营养和每日日记的工具和资源,并通过 Claude 集成进行 AI 辅助分析。
特征
锻炼追踪
记录练习、组数和次数
追踪感知到的努力程度和锻炼后的感受
计算安全训练重量并考虑康复因素
历史锻炼分析
肩部康复支撑
基于RPE的负载管理
营养管理
记录膳食和单个食物项目
追踪蛋白质和卡路里摄入量
监测饥饿和满足程度
每日营养目标和进展
锻炼前/锻炼后营养追踪
进餐时间分析
期刊系统
每日记录心情和精力
睡眠质量和压力水平监测
基于标签的组织
趋势分析和见解
锻炼、营养和幸福感之间的相关性分析
情绪和能量水平的模式识别
安装
通过 Smithery 安装
要通过Smithery自动为 Claude Desktop 安装个人健康追踪器:
npx -y @smithery/cli install personal-mcp --client claude
先决条件
Python 3.10 或更高版本
pip 或 uv 包管理器
使用 pip
pip install -e .
开发安装
git clone https://github.com/yourusername/personal-mcp.git
cd personal-mcp
uv pip install -e ".[dev]"
用法
基本服务器
使用默认设置运行服务器:
personal-mcp run
开发模式
使用热重载运行以进行开发:
personal-mcp dev
MCP 检查器
使用 MCP 检查器进行调试:
personal-mcp inspect
Claude 桌面集成
安装到 Claude 桌面:
personal-mcp install --claude-desktop
配置选项
personal-mcp --help
可用选项:
--name
:设置服务器名称(默认值:“个人助理”)--db-path
:指定数据库位置--dev
:启用开发模式--inspect
:使用 MCP 检查器运行-v, --verbose
:启用详细日志记录
MCP 工具
健身工具
# Log a workout
workout = {
"date": "2024-01-07",
"exercises": [
{
"name": "Bench Press",
"sets": [
{"weight": 135, "reps": 10, "rpe": 7}
]
}
],
"perceived_effort": 8
}
# Calculate training weights
params = {
"exercise": "Bench Press",
"base_weight": 200,
"days_since_surgery": 90,
"recent_pain_level": 2,
"recent_rpe": 7
}
营养工具
# Log a meal
meal = {
"meal_type": "lunch",
"foods": [
{
"name": "Chicken Breast",
"amount": 200,
"unit": "g",
"protein": 46,
"calories": 330
}
],
"hunger_level": 7,
"satisfaction_level": 8
}
# Check nutrition targets
targets = await mcp.call_tool("check_nutrition_targets", {"date": "2024-01-07"})
期刊工具
# Create a journal entry
entry = {
"entry_type": "daily",
"content": "Great workout today...",
"mood": 8,
"energy": 7,
"sleep_quality": 8,
"stress_level": 3,
"tags": ["workout", "recovery"]
}
# Analyze entries
analysis = await mcp.call_tool("analyze_journal_entries", {
"start_date": "2024-01-01",
"end_date": "2024-01-07"
})
发展
运行测试
# Run all tests
pytest
# Run with coverage
pytest --cov=personal_mcp
# Run specific test file
pytest tests/test_database.py
代码质量
# Format code
black src/personal_mcp
# Lint code
ruff check src/personal_mcp
# Type checking
mypy src/personal_mcp
项目结构
personal-mcp/
├── src/
│ └── personal_mcp/
│ ├── tools/
│ │ ├── workout.py
│ │ ├── nutrition.py
│ │ └── journal.py
│ ├── database.py
│ ├── models.py
│ ├── resources.py
│ ├── prompts.py
│ └── server.py
├── tests/
│ ├── test_database.py
│ ├── test_server.py
│ └── test_cli.py
├── pyproject.toml
└── mcp.json
贡献
分叉存储库
创建功能分支
提交你的更改
推送到分支
创建拉取请求
执照
该项目根据 MIT 许可证获得许可 - 有关详细信息,请参阅 LICENSE 文件。
Related MCP Servers
- -securityFlicense-qualityA Model Context Protocol server that provides language models with access to personal Whoop fitness data, allowing queries for cycles, recovery, strain, and workout information from the Whoop API.Last updated -12
- -securityFlicense-qualityA versatile Model Context Protocol server that enables AI assistants to manage calendars, track tasks, handle emails, search the web, and control smart home devices.Last updated -19
- AsecurityAlicenseAqualityA Model Context Protocol server that enables users to access Strava fitness data, including user activities, activity details, segments, and leaderboards through a structured API interface.Last updated -34MIT License
- AsecurityAlicenseAqualityA Model Context Protocol server providing AI assistants with access to healthcare data tools, including FDA drug information, PubMed research, health topics, clinical trials, and medical terminology lookup.Last updated -71450MIT License