CodeBase Optimizer
Analyzes, optimizes, and detects duplicates in codebases for Claude Code.
CodeBase Optimizer MCP Tool
A sophisticated Model Context Protocol (MCP) server that provides comprehensive codebase analysis, optimization, and duplicate detection capabilities for Claude Code.
Features
🔍 Comprehensive Analysis
- Project structure and architecture detection
- Cross-language code duplication detection
- Microservices architecture validation
- Configuration optimization analysis
- Security and performance insights
🤖 AI-Powered Learning
- Pattern recognition that improves with each use
- Project-specific recommendations
- Historical analysis tracking
- Custom rule learning
🚀 Zero Setup Required
- Integrates directly with Claude Code
- No additional installations needed
- Works with any programming language
- Portable across all projects
Available Tools
Individual Analysis Functions
analyze_project_structure- Analyze project organization and architecturedetect_code_duplicates- Find duplicate code across multiple languagesvalidate_microservices_architecture- Validate microservices patternsoptimize_configurations- Analyze configuration managementgenerate_improvement_report- Generate comprehensive actionable report
Master Orchestrator Function
run_complete_project_analysis- 🎯 ONE-COMMAND COMPLETE ANALYSIS- Runs all analyses in optimal order
- Provides prioritized action plan
- Generates health score and improvement roadmap
Installation & Setup
1. Install Dependencies
pip install mcp sqlite3
2. Add to Claude Code MCP Configuration
Add this to your Claude Code MCP configuration:
{
"mcpServers": {
"codebase-optimizer": {
"command": "python",
"args": ["/Users/liadgez/Documents/codebase-optimizer-mcp/server.py"],
"env": {
"PYTHONPATH": "/Users/liadgez/Documents/codebase-optimizer-mcp"
}
}
}
}
3. Restart Claude Code
The tool will be automatically available in all Claude Code sessions.
Usage Examples
Quick Project Health Check
Use run_complete_project_analysis with path "/path/to/your/project"
Focused Duplicate Detection
Use detect_code_duplicates with path "/path/to/project" and languages ["python", "javascript"]
Microservices Validation
Use validate_microservices_architecture with path "/path/to/microservices/project"
Comprehensive Report
Use generate_improvement_report with path "/path/to/project"
Output Examples
Health Score Dashboard
Health Score: 87/100
- Organization Score: 0.9/1.0
- Duplication: 3.2%
- Security Score: 0.95/1.0
Prioritized Recommendations
🔴 HIGH: Address security issues in configuration files
🟡 MEDIUM: Consolidate 12 duplicate functions into shared modules
🟢 LOW: Standardize naming conventions across directories
Action Plan
Phase 1: Critical Issues (1-2 days)
- Fix environment variable exposure
- Remove hardcoded secrets
Phase 2: Improvements (3-5 days)
- Refactor duplicate code blocks
- Standardize API error handling
Supported Languages
- Python (.py)
- JavaScript (.js)
- TypeScript (.ts)
- Java (.java)
- Go (.go)
- Rust (.rs)
- C/C++ (.c, .cpp)
- PHP (.php)
- Ruby (.rb)
Learning & Improvement
The tool automatically:
- Learns patterns from each project analyzed
- Builds knowledge database of common issues
- Improves recommendations based on past successes
- Adapts to your specific coding patterns
Troubleshooting
Common Issues
Tool not appearing in Claude Code:
- Verify MCP configuration path is correct
- Restart Claude Code after adding configuration
- Check Python dependencies are installed
Analysis fails:
- Ensure project path exists and is accessible
- Check that Python can read the project directory
- Verify no permission issues on the project folder
Performance issues:
- Large projects (>10k files) may take longer to analyze
- Use "quick" depth for faster analysis on huge codebases
- Pattern database improves performance over time
Technical Details
Architecture
- Engine: Sophisticated analysis engine with ML pattern recognition
- Database: SQLite for pattern learning and improvement tracking
- MCP Server: Standards-compliant Model Context Protocol implementation
- Extensibility: Plugin system for custom analyzers
Data Storage
- Pattern database stored in
codebase_patterns.db - No sensitive data stored - only patterns and metrics
- Database grows smarter with each project analyzed
Contributing
To extend the tool:
- Add new analyzers to
codebase_optimizer_engine.py - Expose new functions in
server.py - Update tool schema for new parameters
- Test with various project types
License
MIT License - Feel free to use and modify for your projects.
Made with ❤️ for better codebases everywhere
Related Servers
Terraform MCP
A command-line tool that acts as an MCP server to interact with Terraform environments.
Cucumber Studio
Provides LLM access to the Cucumber Studio testing platform for managing and executing tests.
MiniMax MCP
Interact with MiniMax's powerful APIs for text-to-speech, voice cloning, and video/image generation.
Langfuse Prompt Management
Open-source tool for collaborative editing, versioning, evaluating, and releasing prompts.
Sistema de Predicción Energética con IA
An AI-powered system for analyzing and predicting domestic energy consumption. It offers precise forecasts, historical pattern analysis, and personalized optimization recommendations through a conversational interface.
MCP Playground
A playground for MCP implementations featuring multiple microservices, including news and weather examples.
ApostropheCMS
Interact with ApostropheCMS, a Node.js-based content management system, to manage content snippets.
Code Runner MCP
Execute JavaScript and Python code in a secure sandbox. Supports Deno for JS/TS and Pyodide for Python, with configurable permissions.
ndlovu-code-reviewer
Manual code reviews are time-consuming and often miss the opportunity to combine static analysis with contextual, human-friendly feedback. This project was created to experiment with MCP tooling that gives AI assistants access to a purpose-built reviewer. Uses the Gemini cli application to process the reviews at this time and linting only for typescript/javascript apps at the moment. Will add API based calls to LLM's in the future and expand linting abilities. It's also cheaper than using coderabbit ;)
MCP Server with GitHub OAuth
An MCP server with built-in GitHub OAuth support, designed for deployment on Cloudflare Workers.