code-review-mcp
The code-review-mcp server enables automated code reviews using LLMs, designed for integration with AI coding assistants like Claude Code, Cursor, and Windsurf. It reviews git changes with contextual feedback and supports various LLMs including Google, OpenAI, and Anthropic.
What are the prerequisites for using the MCP server?
You need Node.js version 18 or higher, Git installed and accessible in your system's PATH, and API keys for the LLM providers you intend to use.
How do I set up API keys for LLM integration?
API keys should be set as environment variables or placed in a .env file in the root of the project you are reviewing.
What should I do if I encounter a 'Current directory is not a git repository' error?
Ensure you are running the MCP server from the root directory of a valid Git project.
How can I integrate the MCP server with Claude Code?
Add the MCP server in Claude Code using the claude mcp add command with the appropriate environment variables and command configuration.
What should I do if I encounter LLM API errors?
Check the error message for details from the specific LLM API, such as rate limits, invalid model name, or authentication issues.