What is Mcp Codebase Insight

MCP Codebase Insight is a system designed for analyzing and understanding codebases through semantic analysis, pattern detection, and documentation management.

Use cases

Use cases include analyzing legacy code for better maintenance, detecting patterns in code for optimization, and managing documentation for large codebases.

How to use

To use MCP Codebase Insight, install it via pip with ‘pip install mcp-codebase-insight’. Then, you can create an instance of CodebaseAnalyzer and call the analyze_code method with the path to your code.

Key features

Key features include a core vector store system, a basic knowledge base, SSE integration, and a testing framework. Ongoing developments focus on documentation management, advanced pattern detection, performance optimization, and integration testing.

Where to use

MCP Codebase Insight can be used in software development environments, particularly for projects that require deep analysis of codebases to improve understanding and documentation.

MCP Codebase Insight - WIP

🚧 Development in Progress

This project is actively under development. Features and documentation are being continuously updated.

Overview

MCP Codebase Insight is a system for analyzing and understanding codebases through semantic analysis, pattern detection, and documentation management.

Current Development Status

Completed Features

• ✅ Core Vector Store System
• ✅ Basic Knowledge Base
• ✅ SSE Integration
• ✅ Testing Framework
• ✅ TDD and Debugging Framework (rules_template integration)

In Progress

• 🔄 Documentation Management System
• 🔄 Advanced Pattern Detection
• 🔄 Performance Optimization
• 🔄 Integration Testing
• 🔄 Debugging Utilities Enhancement

Planned

• 📋 Extended API Documentation
• 📋 Custom Pattern Plugins
• 📋 Advanced Caching Strategies
• 📋 Deployment Guides
• 📋 Comprehensive Error Tracking System

Quick Start

1. Installation

   pip install mcp-codebase-insight
   

2. Basic Usage

   from mcp_codebase_insight import CodebaseAnalyzer
   
   analyzer = CodebaseAnalyzer()
   results = analyzer.analyze_code("path/to/code")
   

3. Running Tests

   # Run all tests
   pytest tests/
   
   # Run unit tests
   pytest tests/unit/
   
   # Run component tests
   pytest tests/components/
   
   # Run tests with coverage
   pytest tests/ --cov=src --cov-report=term-missing
   

4. Debugging Utilities

   from mcp_codebase_insight.utils.debug_utils import debug_trace, DebugContext, get_error_tracker
   
   # Use debug trace decorator
   @debug_trace
   def my_function():
       # Implementation
   
   # Use debug context
   with DebugContext("operation_name"):
       # Code to debug
   
   # Track errors
   try:
       # Risky operation
   except Exception as e:
       error_id = get_error_tracker().record_error(e, context={"operation": "description"})
       print(f"Error recorded with ID: {error_id}")
   

Testing and Debugging

Test-Driven Development

This project follows Test-Driven Development (TDD) principles:

1. Write a failing test first (Red)
2. Write minimal code to make the test pass (Green)
3. Refactor for clean code while keeping tests passing (Refactor)

Our TDD documentation can be found in docs/tdd/workflow.md.

Debugging Framework

We use Agans’ 9 Rules of Debugging:

1. Understand the System
2. Make It Fail
3. Quit Thinking and Look
4. Divide and Conquer
5. Change One Thing at a Time
6. Keep an Audit Trail
7. Check the Plug
8. Get a Fresh View
9. If You Didn’t Fix It, It Isn’t Fixed

Learn more about our debugging approach in docs/debuggers/agans_9_rules.md.

Documentation

• System Architecture
• Core Components
• API Reference
• Development Guide
• Workflows
• TDD Workflow
• Debugging Practices

Contributing

We welcome contributions! Please see our Contributing Guide for details.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Support

• Issue Tracker
• Discussions