mcp-code-reviewer

mcp-code-reviewer

An MCP server for automatic code review using OpenRouter, enabling performance, clean code, SOLID, async, error handling, and security analysis with direct file modification.

Category
访问服务器

README

MCP PR Review

An MCP (Model Context Protocol) server for automatic code review using OpenRouter as the LLM provider.

🚀 Features

  • Intelligent code review: Analyzes your code and suggests improvements based on:
    • Performance optimizations
    • Clean Code principles
    • SOLID principles application
    • Proper async handling
    • Error handling
    • Security best practices
  • Multiple LLM support: Uses OpenRouter to access different models
  • Direct file modification: Inserts JSDoc review comments directly into your files
  • Easy integration: Connects with any MCP-compatible client

📋 Requirements

  • Node.js >= 18.0.0
  • Yarn 4
  • OpenRouter API Key

🛠️ Installation

  1. Clone the repository
git clone <your-repo>
cd mcp-pr-review
  1. Install dependencies:
yarn install
  1. Configure environment variables:
cp .env.example .env

Edit the .env file and add your OpenRouter API key:

OPENROUTER_API_KEY=your_api_key_here
OPENROUTER_MODEL=moonshotai/kimi-k2:free

🔑 Getting OpenRouter API Key

  1. Go to OpenRouter
  2. Create an account
  3. Generate an API key in your dashboard
  4. Add it to your .env file

🚀 Usage

Running the server

# Production mode
yarn start

# Development mode (with watch)
yarn dev

Using MPC client

Add this configuration to your MCP configuration file:

{
  "mcpServers": {
    "code-review": {
      "command": "node",
      "args": ["path/to/mcp-pr-review/src/index.js"],
      "env": {
        "OPENROUTER_API_KEY": "your_api_key_here"
      }
    }
  }
}

Available Tools

review

Reviews a code file and inserts JSDoc review comments directly into the file.

Parameters:

  • file_path (string): Absolute path to the file you want to review

Important notes:

  • ⚠️ Only absolute paths are accepted (paths starting with /)
  • 📝 The tool modifies the original file by inserting JSDoc comments
  • 🔍 Review categories include: SOLID, PERFORMANCE, ASYNC, ERROR_HANDLING, CLEAN_CODE, SECURITY

Example usage:

# In your MCP client (like Claude Desktop)
/review /Users/username/project/src/myfile.js

What the tool does:

  1. Reads the specified file
  2. Analyzes the code for issues
  3. Generates JSDoc comments with @fixme annotations
  4. Inserts these comments directly into the file before problematic lines
  5. Saves the modified file

Example output format:

/**
 * @fixme PERFORMANCE: Consider using more efficient algorithm
 * @example Use Map instead of nested loops for O(1) lookups
 */
function inefficientFunction() {
  // your code here
}

🔧 Configuration

Environment Variables

Variable Description Default Required
OPENROUTER_API_KEY Your OpenRouter API key -
OPENROUTER_API_URL API base URL https://openrouter.ai/api/v1
OPENROUTER_MODEL Model to use moonshotai/kimi-k2:free

Recommended Models

  • Free models:

    • moonshotai/kimi-k2:free
    • meta-llama/llama-3.1-8b-instruct:free
    • google/gemini-flash-1.5
  • Paid models (better quality):

    • anthropic/claude-3-haiku:beta
    • microsoft/wizardlm-2-8x22b
    • anthropic/claude-3-sonnet:beta

🧪 Development

Project Structure

mcp-pr-review/
├── src/
│   └── index.js          # Main MCP server
├── package.json          # Dependencies and scripts
├── .env.example         # Environment variables template
├── .gitignore           # Files to ignore by git
└── README.md            # This documentation

Available Scripts

yarn start     # Run in production
yarn dev       # Run in development mode
yarn test      # Run tests (not implemented yet)

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选