Interact with CodeRabbit AI reviews on GitHub pull requests.
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.
/coderabbit-review
slash command for complete review processingNo installation required! Run directly with npx:
# Install the latest stable version explicitly
npx coderabbitai-mcp@latest
repo
(for private repos) or public_repo
(for public only)To use the CodeRabbit MCP server in Claude Desktop, add it to your configuration file:
Configuration file locations:
~/Library/Application Support/Claude/claude_desktop_config.json
%APPDATA%/Claude/claude_desktop_config.json
~/.config/Claude/claude_desktop_config.json
Step-by-step setup:
{
"mcpServers": {
"coderabbitai": {
"command": "npx",
"args": ["coderabbitai-mcp@latest"],
"env": {
"GITHUB_PAT": "ghp_your_token_here"
}
}
}
}
ghp_your_token_here
with your actual GitHub Personal Access TokenTo use the CodeRabbit MCP server in Claude Code, configure it in your project:
Step-by-step setup:
Create a .claude
directory 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"
}
}
}
}
ghp_your_token_here
with your actual GitHub Personal Access TokenPro 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.
Use the built-in MCP prompt for complete workflow automation:
/coderabbit-review owner:bradthebeeble repo:wiseguys pullNumber:15
This prompt automatically:
get_coderabbit_reviews
Get all CodeRabbit reviews for a specific pull request.
{
"owner": "bradthebeeble",
"repo": "wiseguys",
"pullNumber": 15
}
get_review_details
Get detailed information about a specific CodeRabbit review.
{
"owner": "bradthebeeble",
"repo": "wiseguys",
"pullNumber": 15,
"reviewId": 2969007538
}
get_review_comments
Get all individual line comments from CodeRabbit reviews.
{
"owner": "bradthebeeble",
"repo": "wiseguys",
"pullNumber": 15,
"reviewId": 2969007538
}
get_comment_details
Get detailed information about a specific CodeRabbit comment.
{
"owner": "bradthebeeble",
"repo": "wiseguys",
"commentId": 2173534099
}
resolve_comment
Mark a CodeRabbit comment as resolved.
{
"owner": "bradthebeeble",
"repo": "wiseguys",
"commentId": 2173534099,
"resolution": "addressed",
"note": "Implemented asyncHandler wrapper as suggested"
}
For development or local customization:
git clone https://github.com/bradthebeeble/coderabbitai-mcp.git
cd coderabbitai-mcp
npm install
npm run build
# Build TypeScript
npm run build
# Watch mode for development
npm run dev
# Clean build files
npm run clean
# Test the server
npm test
Create a .env
file (optional):
# GitHub Configuration (shorter variable name)
GITHUB_PAT=ghp_your_token_here
# Optional: CodeRabbit MCP Configuration
CODERABBIT_LOG_LEVEL=info
Server not loading (NPX):
node --version
npx coderabbitai-mcp
GitHub API errors:
No CodeRabbit reviews found:
Enable debug logging:
CODERABBIT_LOG_LEVEL=debug npx coderabbitai-mcp
/coderabbit-review
promptThe GitHub Personal Access Token needs these permissions:
repo
(for private repositories) or public_repo
(for public only)read:org
(if accessing organization repositories)The server respects GitHub's API rate limits:
git checkout -b feature-name
npm run build
MIT
Enable your code gen agents to create & run 0-config end-to-end tests against new code changes in remote browsers via the Debugg AI testing platform.
A backend service providing tools, resources, and prompts for AI models using the Model Context Protocol (MCP).
Turns any command-line interface (CLI) command into a simple StdIO-based MCP server.
Execute MATLAB scripts and functions via MCP clients. Requires a local MATLAB installation.
An MCP server for Reptor/SysReptor that exposes the reptor CLI tool as a programmable service, configured via environment variables.
Interact with your crash reporting and real using monitoring data on your Raygun account
A RAG-based Q&A server using a vector store built from Gemini CLI documentation.
Integrate Testomat.io API with AI assistants for test management.
Provides interactive user feedback and command execution for AI-assisted development.
Captures and manages stdout logs from multiple processes via a named pipe system for real-time debugging and analysis.