Boostcamp MCP Server
Integrates with the Boostcamp fitness platform to provide access to training history, workout programs, custom exercises, and analytics through Claude.
README
Boostcamp MCP Server
A Model Context Protocol (MCP) server for integrating with the Boostcamp fitness platform. This server provides seamless access to your training history, workout programs, custom exercises, and analytics through Claude Desktop and Claude Code.
Built with the boostcamp-api Python library - A library for interacting with Boostcamp's private API.
🚀 Quick Start
1. Installation
-
Clone this repository:
git clone https://github.com/Alex-Keyes/boostcamp-mcp.git cd boostcamp-mcp -
Install dependencies: Using
uv:uv sync -
Configure Claude Desktop: Add this to your Claude Desktop configuration file:
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:%APPDATA%\Claude\claude_desktop_config.json{ "mcpServers": { "Boostcamp": { "command": "uv", "args": [ "run", "--with", "mcp[cli]", "--with-editable", "/path/to/your/boostcamp-mcp", "mcp", "run", "/path/to/your/boostcamp-mcp/src/boostcamp_mcp/server.py" ] } } }Important: Replace
/path/to/your/boostcamp-mcpwith your actual path! -
Restart Claude Desktop
2. One-Time Authentication Setup
Important: For security, authentication is performed via a standalone script to generate a session.
Open Terminal and run:
cd /path/to/your/boostcamp-mcp
uv run login
Follow the prompts:
- Enter your Boostcamp email and password.
- The script will securely authenticate and save your session locally.
- Session tokens are stored in a
.envfile and.boostcamp/directory (automatically ignored by git).
3. Start Using
Once authenticated, use these tools directly in Claude:
get_my_profile- View your profile and general stats.list_enrolled_programs- See your current active programs.get_training_history- Review your past workouts.get_home_summary- Get your dashboard streak and totals.
✨ Features
📊 Fitness Analytics
- Home Summary: Get total workouts, total weight moved, and current week streak.
- Volume Charts: Access training volume data over time.
- Muscle Distribution: See which muscle groups you've been targeting.
🏋️ Workout Management
- Program Details: Fetch full workout plans, including sets, reps, and coach notes.
- Enrolled Programs: Track your progress in active training plans.
- Custom Exercises: Access exercises you've manually created.
📚 Content & Discovery
- Program Catalog: Search and list all available programs on the platform.
- Blog Access: Read the latest articles and training guides from the Boostcamp blog.
🛠️ Available Tools
| Tool | Description | Parameters |
|---|---|---|
get_my_profile |
Get user profile and settings | None |
list_enrolled_programs |
List your active programs | None |
get_training_history |
Get detailed workout history | timezone_offset |
get_payment_history |
View your subscription/orders | None |
list_custom_exercises |
List your unique exercises | None |
list_all_programs |
Search the program catalog | page, page_size, keyword |
get_program_details |
Get full plan for a program ID | program_id |
list_blogs |
List recent blog posts | page, page_size |
get_home_summary |
Dashboard stats (streak/totals) | timezone_offset |
get_home_chart |
Training volume chart data | timezone_offset |
get_home_muscle |
Muscle group distribution | timezone_offset |
🔧 Troubleshooting
Authentication Issues
If you see "Authentication Error" or token expiration messages:
- Run the login command:
uv run login - Restart your MCP client (Claude Desktop or Claude Code).
Session Management
- Sessions are stored in
.boostcamp/session.pickle. - The
BOOSTCAMP_AUTH_TOKENis saved to your local.env. - Security Note: Never commit your
.envor.boostcamp/folder. They are included in.gitignoreby default.
📄 License
MIT License
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。
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。
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。
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。
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。
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。
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。
mcp-server-qdrant
这个仓库展示了如何为向量搜索引擎 Qdrant 创建一个 MCP (Managed Control Plane) 服务器的示例。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。