MCP Creator Growth

A context-aware learning assistant for AI coding that helps developers learn from AI-generated code changes through interactive quizzes and debug experience tracking.

Why This Tool?

When AI writes code for you, do you actually learn? This MCP server creates a blocking learning session that:

• Waits until you complete an interactive quiz about the changes

• Tracks your debugging experiences for future reference (RAG-based)

• Helps you build real understanding, not just copy-paste habits

Features

• Blocking Learning Sessions - Agent pauses until you complete the learning card

• Interactive Quizzes - Verify your understanding with targeted questions

• 5-Why Reasoning - Understand the "why" behind code decisions

• Debug Experience RAG - Search and record debugging solutions for reuse

• Token-Efficient - Designed to minimize unnecessary AI output

Quick Start

One-Line Installation

Windows (PowerShell):

macOS / Linux:

Manual Installation

1. Clone the repository:

   git clone https://github.com/SunflowersLwtech/mcp_creator_growth.git cd mcp_creator_growth

2. Create virtual environment:

   python -m venv venv # Windows .\venv\Scripts\activate # macOS/Linux source venv/bin/activate

3. Install dependencies:

   pip install -e ".[dev]"

Configure Claude Code

Add the following to your Claude Code MCP settings:

Windows:

macOS / Linux:

Then restart Claude Code.

Usage

Available Tools

Trigger Learning Session

Say to Claude:

• "Quiz me on this change"

• "Test my understanding"

• "Help me learn about what you did"

The agent will create an interactive learning card and wait until you complete it.

Debug Tools

The debug tools work silently in the background:

• When Claude encounters an error, it searches your past solutions

• When Claude fixes an error, it records the solution for future use

Updating

Windows:

macOS / Linux:

Then restart Claude Code.

Configuration

Create ~/.config/mcp-sidecar/config.toml (Unix) or %APPDATA%/mcp-sidecar/config.toml (Windows):

Data Storage

All data is stored locally:

• Project-level: {project}/.mcp-sidecar/ (tracked with git if you want)

• Global: ~/.config/mcp-sidecar/ (personal, never tracked)

Development

Contributing

Contributions are welcome! Please:

1. Fork the repository

2. Create a feature branch (git checkout -b feature/amazing-feature)

3. Commit your changes (git commit -m 'Add amazing feature')

4. Push to the branch (git push origin feature/amazing-feature)

5. Open a Pull Request

License

MIT License - see LICENSE for details.

Acknowledgments

• Built with FastMCP

• Inspired by the need for meaningful AI-assisted learning