MCP Server - Code Review

@arahisman

Repository

Basic information

About MCP Server - Code Review

No overview available yet

#mcp-server #code-review #ai-chat

MCP Server - Code Review config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "mcp-server-code-review": {
      "command": "node",
      "args": [
        "test-mcp-server.js"
      ]
    }
  }
}

MCP Server - Code Review tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is MCP Server - Code Review?

A server implementation for the Model Context Protocol (MCP) that connects Cursor to OpenRouter API via stdio, enabling code review and AI chat functionalities. It is designed for developers using Cursor who want automated code review with project context and access to various large language models.

How to use MCP Server - Code Review?

Install globally or locally via npm (npm install -g mcp-server-code-review). Run from the command line: mcp-server-code-review --api-key YOUR_OPENROUTER_API_KEY [--default-model MODEL_ID]. The server implements two MCP tools: ask for text prompts and code_review for project‑aware code review. Configure the server in Cursor by adding a "mcp-openrouter-stdio" entry using npx with your API key and optional model.

Key features of MCP Server - Code Review

Connects to OpenRouter API for various large language models
Provides ask tool for simple text prompt responses
Provides code_review tool with project context analysis
Integrates with repomix for codebase packaging and analysis
Supports multi‑language project detection automatically
Runs as a stdio server compatible with MCP protocol

Use cases of MCP Server - Code Review

Get AI‑powered answers to coding questions directly in Cursor.
Automate code reviews with context from completed tasks and work reports.
Analyze entire project directories for code quality and suggestions.
Use from any MCP‑compatible editor (e.g., Cursor) for flexible AI chat.

Frequently asked questions

What is the OpenRouter API key and how do I get one?

The API key is required to connect to OpenRouter. You can obtain one at [OpenRouter](https://openrouter.ai).

What are the runtime requirements?

Node.js version 16 or higher and an OpenRouter API key. No other external dependencies are needed.

What LLM models can be used?

Any model available on OpenRouter. The default is `google/gemini-2.0-flash-thinking-exp:free`. You can override it with the `--default-model` option or per‑call in the `code_review` tool.

How does the `code_review` tool differ from the `ask` tool?

The `ask` tool sends a simple text prompt and returns the response. The `code_review` tool includes project‑specific context such as completed tasks, work report, project path, and planned tasks, enabling a more thorough analysis.