Question 1

What is the Code Review MCP Server?

Accepted Answer

The Code Review MCP Server is a tool that uses Large Language Models (LLMs) to perform automated code reviews, identifying potential bugs, security vulnerabilities, and style violations.

Question 2

What is MCP?

Accepted Answer

MCP stands for Model Context Protocol. It is an open protocol designed to standardize how applications provide context to LLMs, enabling AI models to interact with external data sources and tools.

Question 3

Which LLMs are supported?

Accepted Answer

The Code Review MCP Server supports Google Gemini, OpenAI, and Anthropic models through the Vercel AI SDK.

Question 4

How do I install the Code Review MCP Server?

Accepted Answer

The recommended way to install the server is via `npx`: `npx -y @vibesnipe/code-review-mcp`

Question 5

What are the prerequisites for using the server?

Accepted Answer

You need Node.js (version 18 or higher), Git, and API keys for the LLM providers you intend to use.

Question 6

How do I integrate the server with Claude Code?

Accepted Answer

Add the MCP server in Claude Code using the `claude mcp add` command, specifying the path to the server executable or the `npx` command.

Question 7

How do I integrate the server with Cursor?

Accepted Answer

Configure Cursor's rules for code review and add the MCP server in Cursor's settings with the correct command and environment variables.

Question 8

How do I integrate the server with Windsurf?

Accepted Answer

Configure the MCP server in Windsurf's MCP Servers panel and create workflows to invoke the server from Windsurf's Cascade interface.

Question 9

What is the 'perform_code_review' tool?

Accepted Answer

This tool performs a code review using a specified LLM on git changes within the current Git repository. It requires parameters such as target, taskDescription, llmProvider, and modelName.

Question 10

What environment variables do I need to set?

Accepted Answer

You need to set `GOOGLE_API_KEY`, `OPENAI_API_KEY`, or `ANTHROPIC_API_KEY` depending on the LLM provider you are using.

Question 11

Where do I find the smart slash commands for Claude Code?

Accepted Answer

The slash commands are located in the `examples/claude-commands/` directory. Copy them to your project's `.claude/commands/` directory.

Question 12

How do I use the smart slash commands in Claude Code?

Accepted Answer

Invoke the commands in Claude Code with `/project:command-name` (e.g., `/project:review-staged-claude`).

Question 13

What are the security considerations when using this tool?

Accepted Answer

Be mindful of API key handling, git repository analysis, code privacy, and branch name sanitization.

Question 14

What do I do if I get the error 'Current directory is not a git repository...'?

Accepted Answer

Ensure you are running the command from the root directory of a valid Git project.

Question 15

What do I do if I get the error 'API key for ... is not configured'?

Accepted Answer

Make sure the relevant environment variable is set in the shell where you launched the MCP server or in a `.env` file in your project's root.

@VibeSnipe/code-review-mcp

Resources

Project Details

Recomended MCP Servers

Featured Templates

AI Chatbot Starter Kit

Unified Authorization Template

AI Voice Assistant (Voice-Text-Voice)

Image Generation with Stable Diffusion

Multi-language AI Translator

Pharmacy Admin Panel

Start your free trial