logo
Free, unlimited AI code reviews that run on commit
git-lrc git-lrc GitHub Install Now We'd appreciate a star git-lrc - Free, unlimited AI code reviews that run on commit | Product Hunt git-lrc - Free, unlimited AI code reviews that run on commit | Product Hunt

mcp-codebase-insight

Analyzes codebases through semantic analysis and pattern detection, manages architecture decisions, and generates documentation. Enhances development workflows with intelligent insights and AI-assisted debugging.

Author

mcp-codebase-insight logo

tosin2013

No License

Quick Info

GitHub GitHub Stars 11
NPM Weekly Downloads 0
Tools 1
Last Updated 2026-02-19

Tags

codebasecodebasesinsightcodebase insightanalyzes codebasescodebases semantic

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 bash pip install mcp-codebase-insight

  2. Basic Usage ```python from mcp_codebase_insight import CodebaseAnalyzer

analyzer = CodebaseAnalyzer() results = analyzer.analyze_code("path/to/code") ```

  1. Running Tests ```bash # 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 ```

  1. Debugging Utilities ```python 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

See Also

`