MCP Server Demo

🚀 GitHub Code Review MCP Service

An AI-driven GitHub repository code review service powered by Claude.

🚀 Quick Start

This service offers a range of tools that enable users to:

1. Submit GitHub repositories for code review.
2. Obtain detailed feedback and suggestions for the codebase.
3. Focus on specific areas (e.g., security, performance, best practices) during the review.
4. Track review history and access previous review results.

✨ Features

• Repository Analysis: Analyze a GitHub repository by providing its URL.
• Focused Review: Optionally specify areas of focus for the review (e.g., "security, performance, best practices").
• Improvement Suggestions: Receive specific suggestions for improving the codebase.
• File-level Analysis: Get detailed feedback for specific files.
• Security Scan: Identify security vulnerabilities and provide repair suggestions.
• Dependency Analysis: Analyze project dependencies to detect outdated packages and potential vulnerabilities.
• Code Quality Metrics: Gain insights into code complexity, duplication rate, and maintainability.
• Performance Analysis: Identify performance bottlenecks and provide optimization suggestions.
• Best Practice Comparison: Compare the code with industry best practices (framework can be specified).
• Pull Request Description Generation: Automatically generate comprehensive pull request descriptions.
• Cascade Prompt Generation: Create Cascade-specific prompts for implementing improvements.

📚 Documentation

What is MCP?

The Model Context Protocol (MCP) is an open protocol that allows LLM applications to seamlessly integrate with external data sources and tools. Whether you're building an AI-driven IDE, enhancing a chat interface, or creating custom AI workflows, MCP provides a standard way to connect LLMs with the content they need.

🔧 Technical Details

MCP Tools

This MCP server provides the following tools:

Repository Review Tools

• review_repository(repo_url: str, focus_areas: Optional[str] = None): Submit a repository for review via URL, optionally specifying areas of focus.
• list_reviewed_repositories(): List all reviewed repositories.

Improvement Suggestion Tools

• suggest_improvements(repo_url: str): Provide improvement suggestions for a specified repository.
• get_improvement_details(repo_url: str, file_path: str): Get detailed improvement information for a specific file.

Security and Performance Tools

• scan_for_vulnerabilities(repo_url: str): Scan a repository for security vulnerabilities.
• analyze_performance(repo_url: str): Analyze the performance issues of a repository.

Code Generation Tools

• generate_improved_code(repo_url: str, file_path: str): Generate improved code for a specified file.
• create_cascade_prompt(repo_url: str): Create a Cascade prompt for implementing improvements.

📦 Installation

1. Clone the repository:

   git clone https://github.com/your-repository.git
   

2. Set up a virtual environment and install dependencies:

   python -m venv env
   source env/bin/activate  # Use `env\Scripts\activate` on Windows
   pip install -r requirements.txt
   

3. Start the server:

   python main.py
   

💻 Usage Examples

Basic Usage

1. Review a repository:

   Please review the GitHub repository at https://github.com/username/repo-name
   

2. Focus on specific areas during the review:

   Review https://github.com/username/repo-name with focus on security and performance
   

3. Get improvement suggestions:

   Suggest improvements for the repository https://github.com/username/repo-name
   

4. List reviewed repositories:

   Show me all the repositories that have been reviewed
   

5. Generate a Cascade prompt:

   Generate a Cascade prompt for the improvements to https://github.com/username/repo-name
   

6. Get improved code:

   Show me improved code for the file src/components/Button.js in https://github.com/username/repo-name
   

📄 License

MIT

References

• Model Context Protocol (MCP) Python SDK - The official Python SDK for building MCP providers