CodeRabbit MCP Server
Enables LLMs to retrieve, analyze, and programmatically implement CodeRabbit AI code review suggestions on GitHub pull requests, with automated workflows for processing and resolving review comments.
README
CodeRabbit MCP Server
A Model Context Protocol (MCP) server for interacting with CodeRabbit AI reviews on GitHub pull requests. This server enables Large Language Models (LLMs) to analyze, understand, and implement CodeRabbit suggestions programmatically.
Features
- Get CodeRabbit Reviews: Retrieve all CodeRabbit reviews for a specific pull request
- Review Details: Get detailed information about specific reviews including configuration and files reviewed
- Extract Comments: Get individual line comments with AI prompts and suggestions
- Comment Details: Deep dive into specific comments with context and fix examples
- Resolve Comments: Mark comments as addressed, won't fix, or not applicable
- Automated Workflow Prompt: Use
/coderabbit-reviewslash command for complete review processing
Quick Start
Installation (NPX - Recommended)
No installation required! Run directly with npx:
# Install the latest stable version explicitly
npx coderabbitai-mcp@latest
Prerequisites
- GitHub Personal Access Token: Create at https://github.com/settings/tokens
- Required scopes:
repo(for private repos) orpublic_repo(for public only)
- Required scopes:
- Node.js 18+: Required for running the server
Configuration
Claude Desktop Configuration
To use the CodeRabbit MCP server in Claude Desktop, add it to your configuration file:
Configuration file locations:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%/Claude/claude_desktop_config.json - Linux:
~/.config/Claude/claude_desktop_config.json
Step-by-step setup:
- Open your Claude Desktop configuration file (create it if it doesn't exist)
- Add the CodeRabbit MCP server configuration:
{
"mcpServers": {
"coderabbitai": {
"command": "npx",
"args": ["coderabbitai-mcp@latest"],
"env": {
"GITHUB_PAT": "ghp_your_token_here"
}
}
}
}
- Replace
ghp_your_token_herewith your actual GitHub Personal Access Token - Save the file and restart Claude Desktop
Claude Code Configuration
To use the CodeRabbit MCP server in Claude Code, configure it in your project:
Step-by-step setup:
-
Create a
.claudedirectory in your project root (if it doesn't exist):mkdir .claude -
Create or edit
.claude/config.json:
{
"mcpServers": {
"coderabbitai": {
"command": "npx",
"args": ["coderabbitai-mcp@latest"],
"env": {
"GITHUB_PAT": "ghp_your_token_here"
}
}
}
}
- Replace
ghp_your_token_herewith your actual GitHub Personal Access Token - The server will be available next time you start Claude Code in this project
Pro tip: For security, you can use environment variables instead of hardcoding the token:
{
"mcpServers": {
"coderabbitai": {
"command": "npx",
"args": ["coderabbitai-mcp@latest"],
"env": {
"GITHUB_PAT": "${GITHUB_PAT}"
}
}
}
}
Then set the GITHUB_PAT environment variable in your shell before starting Claude Code.
Usage
Automated Review Processing (Recommended)
Use the built-in MCP prompt for complete workflow automation:
/coderabbit-review owner:bradthebeeble repo:wiseguys pullNumber:15
This prompt automatically:
- Finds and analyzes CodeRabbit reviews
- Classifies issues by priority (high/medium/low)
- Gets your approval before making changes
- Systematically implements fixes
- Marks resolved comments in CodeRabbit
- Provides a completion summary
Manual Tool Usage
<details> <summary>Available Tools</summary>
1. get_coderabbit_reviews
Get all CodeRabbit reviews for a specific pull request.
{
"owner": "bradthebeeble",
"repo": "wiseguys",
"pullNumber": 15
}
2. get_review_details
Get detailed information about a specific CodeRabbit review.
{
"owner": "bradthebeeble",
"repo": "wiseguys",
"pullNumber": 15,
"reviewId": 2969007538
}
3. get_review_comments
Get all individual line comments from CodeRabbit reviews.
{
"owner": "bradthebeeble",
"repo": "wiseguys",
"pullNumber": 15,
"reviewId": 2969007538
}
4. get_comment_details
Get detailed information about a specific CodeRabbit comment.
{
"owner": "bradthebeeble",
"repo": "wiseguys",
"commentId": 2173534099
}
5. resolve_comment
Mark a CodeRabbit comment as resolved.
{
"owner": "bradthebeeble",
"repo": "wiseguys",
"commentId": 2173534099,
"resolution": "addressed",
"note": "Implemented asyncHandler wrapper as suggested"
}
</details>
<details> <summary>Development Installation</summary>
For development or local customization:
git clone https://github.com/bradthebeeble/coderabbitai-mcp.git
cd coderabbitai-mcp
npm install
npm run build
Development Commands
# Build TypeScript
npm run build
# Watch mode for development
npm run dev
# Clean build files
npm run clean
# Test the server
npm test
</details>
<details> <summary>Environment Variables</summary>
Create a .env file (optional):
# GitHub Configuration (shorter variable name)
GITHUB_PAT=ghp_your_token_here
# Optional: CodeRabbit MCP Configuration
CODERABBIT_LOG_LEVEL=info
</details>
<details> <summary>Troubleshooting</summary>
Common Issues
Server not loading (NPX):
- Verify Node.js 18+ is installed:
node --version - Test npx execution manually:
npx coderabbitai-mcp - Check your internet connection (npx downloads the latest version)
GitHub API errors:
- Verify your GitHub token has the required permissions
- Check that you have access to the repositories you're querying
No CodeRabbit reviews found:
- Verify the PR has CodeRabbit reviews (check GitHub web interface)
- Ensure you're using the correct owner/repo/pullNumber
Debug Mode
Enable debug logging:
CODERABBIT_LOG_LEVEL=debug npx coderabbitai-mcp
</details>
Integration Requirements
Supported AI Clients
- Claude Desktop: Full support with configuration
- Claude Code: Project-level MCP integration with
/coderabbit-reviewprompt - Other MCP Clients: Any client supporting the Model Context Protocol
Authentication
The GitHub Personal Access Token needs these permissions:
repo(for private repositories) orpublic_repo(for public only)read:org(if accessing organization repositories)
Architecture
- TypeScript: Fully typed implementation with Zod validation
- MCP SDK: Built on the official Model Context Protocol SDK
- Modular Design: Each tool is implemented in its own module
- MCP Prompts: Automated workflows available as slash commands
API Rate Limits
The server respects GitHub's API rate limits:
- 5,000 requests/hour for authenticated requests
- Automatically handles rate limit responses
Contributing
- Fork the repository
- Create a feature branch:
git checkout -b feature-name - Make your changes and add tests
- Run the build:
npm run build - Submit a pull request
License
MIT
Support
- Issues: GitHub Issues
- Discussions: GitHub Discussions
- Documentation: Full examples available in EXAMPLES.md
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。