Code ReviewSAFE

A custom MCP server that performs code reviews using Repomix and LLMs.

Features

• Flatten codebases using Repomix
• Analyze code with Large Language Models
• Get structured code reviews with specific issues and recommendations
• Support for multiple LLM providers (OpenAI, Anthropic, Gemini)
• Handles chunking for large codebases

Installation

# Clone the repository
git clone https://github.com/yourusername/code-review-server.git
cd code-review-server

# Install dependencies
npm install

# Build the server
npm run build

Configuration

Create a .env file in the root directory based on the .env.example template:

cp .env.example .env

Edit the .env file to set up your preferred LLM provider and API key:

# LLM Provider Configuration
LLM_PROVIDER=OPEN_AI
OPENAI_API_KEY=your_openai_api_key_here

Usage

As an MCP Server

The code review server implements the Model Context Protocol (MCP) and can be used with any MCP client:

# Start the server
node build/index.js

The server exposes two main tools:

1. analyze_repo: Flattens a codebase using Repomix
2. code_review: Performs a code review using an LLM

When to Use MCP Tools

This server provides two distinct tools for different code analysis needs:

analyze_repo

Use this tool when you need to:

• Get a high-level overview of a codebase's structure and organization
• Flatten a repository into a textual representation for initial analysis
• Understand the directory structure and file contents without detailed review
• Prepare for a more in-depth code review
• Quickly scan a codebase to identify relevant files for further analysis

Example situations:

• "I want to understand the structure of this repository before reviewing it"
• "Show me what files and directories are in this codebase"
• "Give me a flattened view of the code to understand its organization"

code_review

Use this tool when you need to:

• P