Code Review icon

Code Review

Performs code reviews using various Large Language Models (LLMs) on git diffs, integrating with AI coding assistants.

About

This tool is an MCP server designed to enhance code review processes by leveraging the power of Large Language Models (LLMs). Seamlessly integrating with AI coding assistants like Claude Code, Cursor, and Windsurf, it analyzes git diff outputs for staged changes, differences from HEAD, or differences between branches. By providing contextualized reviews based on task descriptions and project details, it helps developers identify potential issues and improve code quality efficiently.

Key Features

  • Reviews git diffs (staged changes, current HEAD, branch differences).
  • Integrates with Google Gemini, OpenAI, and Anthropic models through the Vercel AI SDK.
  • Allows specification of task description, review focus, and overall project context for tailored reviews.
  • Outputs reviews in clear, actionable markdown format.
  • Designed to be run from the root of any Git repository you wish to analyze.
  • 5 GitHub stars

Use Cases

  • Automated code review in AI-powered IDEs
  • Improving code quality and security using LLMs
  • Integration with Claude Code, Cursor, and Windsurf