
Security News
Anthropic Identifies Biased Reasoning and Recklessness as Drivers of Claude’s PyPI Attack
Anthropic found biased reasoning and recklessness drove Claude Mythos 5 to publish malware on PyPI and compromise a security vendor.
coderabbitai-mcp
Advanced tools
MCP server for interacting with CodeRabbit AI reviews on GitHub pull requests. Enables LLMs to analyze, implement, and resolve CodeRabbit suggestions programmatically.
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)Add to your Claude Desktop configuration file:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%/Claude/claude_desktop_config.json
{
"mcpServers": {
"coderabbitai": {
"command": "npx",
"args": ["coderabbitai-mcp"],
"env": {
"GITHUB_PAT": "ghp_your_token_here"
}
}
}
}
Add to your project's .claude/config.json:
{
"mcpServers": {
"coderabbitai": {
"command": "npx",
"args": ["coderabbitai-mcp"],
"env": {
"GITHUB_PAT": "ghp_your_token_here"
}
}
}
}
Use the built-in MCP prompt for complete workflow automation:
/coderabbit-review owner:bradthebeeble repo:wiseguys pullNumber:15
This prompt automatically:
get_coderabbit_reviewsGet all CodeRabbit reviews for a specific pull request.
{
"owner": "bradthebeeble",
"repo": "wiseguys",
"pullNumber": 15
}
get_review_detailsGet detailed information about a specific CodeRabbit review.
{
"owner": "bradthebeeble",
"repo": "wiseguys",
"pullNumber": 15,
"reviewId": 2969007538
}
get_review_commentsGet all individual line comments from CodeRabbit reviews.
{
"owner": "bradthebeeble",
"repo": "wiseguys",
"pullNumber": 15,
"reviewId": 2969007538
}
get_comment_detailsGet detailed information about a specific CodeRabbit comment.
{
"owner": "bradthebeeble",
"repo": "wiseguys",
"commentId": 2173534099
}
resolve_commentMark 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 --versionnpx coderabbitai-mcpGitHub 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-namenpm run buildMIT
FAQs
MCP server for interacting with CodeRabbit AI reviews on GitHub pull requests. Enables LLMs to analyze, implement, and resolve CodeRabbit suggestions programmatically.
The npm package coderabbitai-mcp receives a total of 1,241 weekly downloads. As such, coderabbitai-mcp popularity was classified as popular.
We found that coderabbitai-mcp demonstrated a not healthy version release cadence and project activity because the last version was released a year ago. It has 1 open source maintainer collaborating on the project.

Security News
Anthropic found biased reasoning and recklessness drove Claude Mythos 5 to publish malware on PyPI and compromise a security vendor.

Research
/Security News
Malicious Chrome and Firefox extensions target Axiom Trade and Padre users, stealing session tokens and wallet data.

Security News
GPT-6 Astra hits 100% on ExploitBench and finds zero-days autonomously, while independent tests reveal scope violations and monitoring gaps.