Learning Hour MCP
An MCP server that generates comprehensive Learning Hour content for Technical Coaches, enabling teams to practice technical excellence through structured deliberate practice sessions.
Tools
generate_session
Generate comprehensive Learning Hour content for Technical Coaches
generate_code_example
Generate detailed before/after code examples for a learning topic
create_miro_board
Create a Miro board from Learning Hour session content
get_miro_auth_url
Generate Miro OAuth authorization URL
test_miro_token
Test if a Miro access token is valid
README
Learning Hour MCP
An MCP server that generates comprehensive Learning Hour content for Technical Coaches, enabling teams to practice technical excellence through structured deliberate practice sessions. Works seamlessly with the Miro MCP for creating interactive boards.
Philosophy
Learning Hours are structured practice sessions where software teams develop technical excellence skills through deliberate practice. Just as athletes and pilots dedicate time to practice their craft, software developers need dedicated time to master fundamental programming practices that stand the test of time.
This MCP server supports the 4C Learning Model (Connect → Concept → Concrete → Conclusion) and focuses on technical practices that enhance agility:
- Test Driven Development (TDD)
- Refactoring techniques
- Clean code principles
- Evolutionary design
- Pairing/ensemble programming
Features
- Generate Session Content: Creates comprehensive Learning Hour materials for any coding topic
- Generate Code Examples: Produces before/after code examples with explanations
- Miro Integration: Direct integration with Miro API to create visual Learning Hour boards
- OAuth Support: Complete OAuth flow for Miro authentication
Tools
generate_session
Generates comprehensive Learning Hour content including objectives, activities, and discussion prompts.
Input:
{
"topic": "Feature Envy"
}
Output: Structured session data with miroContent section ready for Miro board creation.
generate_code_example
Creates detailed before/after code examples for learning topics.
Input:
{
"topic": "Feature Envy",
"language": "javascript"
}
get_miro_auth_url
Generates a Miro OAuth authorization URL for obtaining access tokens.
Input:
{
"redirectUri": "http://localhost:3000/callback",
"state": "optional-security-state"
}
test_miro_token
Tests if a Miro access token is valid and working.
Input:
{
"accessToken": "your_miro_access_token"
}
create_miro_board
Creates a Miro board with Learning Hour content automatically laid out.
Input:
{
"sessionContent": {}, // Output from generate_session
"accessToken": "your_miro_access_token"
}
Setup
- Install dependencies:
npm install
- Configure environment variables:
cp .env.example .env
# Edit .env and add your Anthropic API key
-
Get your API keys:
Anthropic API Key:
- Visit Anthropic Console
- Create an account or sign in
- Generate an API key
- Add it to your
.envfile:ANTHROPIC_API_KEY=your_actual_api_key_here
Miro Integration (Optional):
- Visit Miro Developers
- Create a new app to get Client ID and Client Secret
- Add to your
.envfile:MIRO_CLIENT_ID=your_miro_client_id MIRO_CLIENT_SECRET=your_miro_client_secret
-
Build and run:
npm run build && npm start
Testing
Run the integration tests to verify your API connection:
# Run all tests
npm test
# Run only integration tests
npm run test:integration
Note: Integration tests require a valid ANTHROPIC_API_KEY in your .env file and will make real API calls.
Miro Integration Workflow
Getting a Miro Access Token
To use Miro integration, you need a valid access token. Here are two ways:
Option A: Quick Personal Access Token (Easiest)
- Go to Miro Developer Portal
- Create a developer account
- Create a new app
- Generate a personal access token
- Test it:
test_miro_token {"accessToken": "your_token"}
Option B: OAuth Flow (For Production)
- Get Authorization URL:
{
"tool": "get_miro_auth_url",
"arguments": {
"redirectUri": "http://localhost:3000/callback"
}
}
- Visit the URL, authorize, and exchange the code for a token
Using Miro Integration
- Test Your Token:
{
"tool": "test_miro_token",
"arguments": {
"accessToken": "your_miro_access_token"
}
}
- Generate Learning Session:
{
"tool": "generate_session",
"arguments": {
"topic": "Feature Envy"
}
}
- Create Miro Board:
{
"tool": "create_miro_board",
"arguments": {
"sessionContent": {}, // Use output from step 2
"accessToken": "your_miro_access_token"
}
}
Option 2: Manual Miro Integration
You can also use the structured miroContent output from generate_session with other Miro tools or the Miro web interface.
Environment Variables
ANTHROPIC_API_KEY: Required - your Anthropic API key for generating Learning Hour contentMIRO_CLIENT_ID: Optional - your Miro app client ID for OAuth authenticationMIRO_CLIENT_SECRET: Optional - your Miro app client secret for OAuth authentication
Usage Examples
Generate a complete Learning Hour:
{
"tool": "generate_session",
"arguments": {
"topic": "Single Responsibility Principle"
}
}
Create code examples:
{
"tool": "generate_code_example",
"arguments": {
"topic": "Feature Envy",
"language": "python"
}
}
The output includes structured content perfect for Technical Coaches to run effective Learning Hours with hands-on exercises and group discussions.
Documentation
- Learning Hours Guide - Comprehensive guide to Learning Hours philosophy and implementation
- Domain Vocabulary - Key terms and concepts used in Learning Hours
- Coding Style Guidelines - Code style aligned with clean code principles
Learning Outcomes
Teams practicing Learning Hours experience:
- Frequent deployments with minimal defects
- Faster development velocity
- Higher quality software delivery
- Improved team morale and collaboration
- Reduced technical debt
"Continuous attention to technical excellence and good design enhances agility" - The 9th principle of the Agile Manifesto
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。