learning-hour-mcp
Create Learning Hours on a shared whiteboard from your favorite MCP client
Documentation
learning-hour-mcp
Generate Learning Hour content for Technical Coaches using AI. Create structured practice sessions that help development teams master technical excellence through the 4C Learning Model.
What is this?
An MCP server that helps Technical Coaches run Learning Hours - structured 60-minute practice sessions where teams improve their coding skills through deliberate practice. It generates session plans, code examples, and can even create interactive Miro boards.
Who is this for?
- Technical Coaches facilitating team learning sessions
- Team Leads wanting to improve their team's technical practices
- Developers organizing coding dojos or practice sessions
Installation
Prerequisites
1. Claude Desktop - Install the desktop app
2. Anthropic API Key - Sign up and create a key ($5 free credit for new accounts)
Complete Setup
Choose your preferred editor:
Claude Desktop
Add to your Claude Desktop configuration:
{
"mcpServers": {
"learning-hour": {
"command": "npx",
"args": ["-y", "learning-hour-mcp"],
"env": {
"ANTHROPIC_API_KEY": "your-anthropic-key",
"MIRO_ACCESS_TOKEN": "your-miro-token-optional",
"GITHUB_TOKEN": "your-github-token-optional"
}
}
}
}Configuration steps:
1. Open Claude Desktop settings (cmd/ctrl + ,)
2. Go to "Developer" → "Edit Config"
3. Paste the configuration above
4. Replace `your-anthropic-key` with your actual key
5. Save and restart Claude Desktop
VSCode
Add to your VSCode settings.json:
{
"mcp.servers": {
"learning-hour": {
"command": "npx",
"args": ["-y", "learning-hour-mcp"],
"env": {
"ANTHROPIC_API_KEY": "your-anthropic-key",
"MIRO_ACCESS_TOKEN": "your-miro-token-optional",
"GITHUB_TOKEN": "your-github-token-optional"
}
}
}
}Configuration steps:
1. Install the MCP VSCode Extension
2. Open settings.json (Cmd/Ctrl+Shift+P → "Preferences: Open Settings (JSON)")
3. Add the configuration above
4. Replace tokens with your actual values
5. Reload VSCode window (Cmd/Ctrl+Shift+P → "Developer: Reload Window")
Cursor
Add to your Cursor configuration:
{
"mcpServers": {
"learning-hour": {
"command": "npx",
"args": ["-y", "learning-hour-mcp"],
"env": {
"ANTHROPIC_API_KEY": "your-anthropic-key",
"MIRO_ACCESS_TOKEN": "your-miro-token-optional",
"GITHUB_TOKEN": "your-github-token-optional"
}
}
}
}Configuration steps:
1. Open Cursor settings (Cmd/Ctrl + ,)
2. Click on "Features" → "Claude" → "Advanced"
3. Add the MCP server configuration
4. Replace tokens with your actual values
5. Restart Cursor
Required: Only `ANTHROPIC_API_KEY` is required. The other tokens enable additional features.
Quick Start
After installation, try this in Claude:
> "Use the learning hour tools to create a session about the Extract Method refactoring"
Claude will generate a complete 60-minute session plan with:
- Opening connection activity
- Concept introduction
- Hands-on coding exercise
- Reflection and commitment
Available Tools
`generate_session`
Generate a complete Learning Hour session plan with activities following the 4C model (Connect, Concept, Concrete, Conclusion).
{
"topic": "Feature Envy"
}`generate_code_example`
Create before/after code examples for a specific topic.
{
"topic": "Extract Method",
"language": "typescript"
}`create_miro_board`
Create a new Miro board or add frames to an existing board (requires `MIRO_ACCESS_TOKEN`).
{
"sessionContent": { /* from generate_session */ },
"existingBoardId": "optional-board-id" // If provided, adds frames to existing board
}`list_miro_boards`
List all Miro boards accessible with your token (requires `MIRO_ACCESS_TOKEN`).
{
"limit": 50, // Optional, max 50
"cursor": "optional-pagination-cursor"
}`get_miro_board`
Get details about a specific Miro board (requires `MIRO_ACCESS_TOKEN`).
{
"boardId": "board-id-to-get"
}`delete_miro_board`
Delete a Miro board (requires `MIRO_ACCESS_TOKEN`). Use with caution!
{
"boardId": "board-id-to-delete",
"confirm": true // Required safety check
}`analyze_repository`
Find real code examples in GitHub repositories (requires `GITHUB_TOKEN`).
`analyze_tech_stack`
Analyze a repository's technology stack to create team-specific content (requires `GITHUB_TOKEN`).
Optional Features
Enable Miro Board Creation
*Transform your Learning Hour into a visual, interactive workshop board*
Get a Miro token:
- Go to Miro Apps
- Create a new app (name it "Learning Hours")
- Copy the access token
- Add as `MIRO_ACCESS_TOKEN` in your config
Enable Repository Analysis
*Find real code examples from your team's actual codebase*
Create a GitHub Personal Access Token:
- Name: "Learning Hour MCP"
- Expiration: 90 days (recommended)
- Permissions: `repo` (read access)
- Add as `GITHUB_TOKEN` in your config
Learn More
- Diamante Technical Coaching - Refactor to Grow Newsletter
- SammanCoaching.org - Technical coaching resources and Learning Hour guides
- Learning Hours - Catalog of Learning Hour topics
- 4C Learning Model - Connect, Concept, Concrete, Conclusion
- Technical Coaching - Role and practices
Troubleshooting
"Tool not found" error: Make sure you restarted Claude Desktop after adding the configuration.
"Invalid API key": Check that you copied the entire key including any prefixes (sk-ant-...).
Miro board not creating: Check that your MIRO_ACCESS_TOKEN is valid and has board creation permissions.
Contributing
See CONTRIBUTING.md for development setup and guidelines.
License
MIT
Frequently asked questions
What is learning-hour-mcp?
learning-hour-mcp is Create Learning Hours on a shared whiteboard from your favorite MCP client
How do I install learning-hour-mcp?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is learning-hour-mcp open source?
Yes — it is hosted on GitHub at https://github.com/SDiamante13/learning-hour-mcp and has 6 stars.
Related MCP tools
Model Context Protocol Servers
The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra
A MCP for Claude Desktop / Claude Code / Windsurf / Cursor to build n8n workflows for you
MCP server to provide Figma layout information to AI coding agents like Cursor
The world's best AI personal assistant for email. Open source app to help you reach inbox zero fast.
Instant is the best backend for AI-coded apps. You get auth, permissions, storage, presence, and streams — everything you need to ship apps your users will love.
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP