Automated Code Review
Automated AI code reviews powered — webhook-driven, real-time dashboard, MCP integration, smart queue with deduplication, multi-agent audits, and iterative follow-up reviews for GitLab MRs and GitHub PRs
What is Automated Code Review?
Automated Code Review is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to automated ai code reviews powered — webhook-driven, real-time dashboard, mcp integration, smart queue with deduplication, multi-agent audits, and iterative follow-up reviews for gitlab mrs and github ...
Automated AI code reviews powered — webhook-driven, real-time dashboard, MCP integration, smart queue with deduplication, multi-agent audits, and iterative follow-up reviews for GitLab MRs and GitHub PRs
This server falls under the Version Control category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Automated AI code reviews powered — webhook-driven, real-tim
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx review-flowConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Automated Code Review
Review Flow is an automated AI code review system that integrates with GitHub PRs and GitLab MRs via webhooks, dispatching multi-agent Claude reviews across dimensions like architecture, security, testing, and code quality. It runs as a persistent daemon with a real-time WebSocket dashboard, smart deduplication queuing, isolated git worktrees per review, and iterative follow-up reviews when developers push fixes — replacing slow manual review cycles with instant, comprehensive AI feedback.
Prerequisites
- Node.js 20+ and npm installed globally
- Claude Code CLI installed and authenticated
- GitHub CLI (gh) with OAuth, or GitLab CLI (glab) with authentication, depending on your platform
- Git with worktree support (Git 2.5+)
- A publicly accessible URL or reverse proxy (e.g., ngrok) to receive webhook events from GitHub/GitLab
Install Review Flow globally
Install the reviewflow CLI package globally via npm.
npm install -g reviewflowRun the interactive setup wizard
The init command walks you through configuring your GitHub/GitLab connection, webhook secrets, Claude Code integration, and dashboard settings.
reviewflow initConfigure webhooks in GitHub or GitLab
In your GitHub repository settings (Settings → Webhooks) or GitLab project settings, add a webhook pointing to your Review Flow server's endpoint. Use the webhook secret shown during init. GitHub endpoint: /webhooks/github, GitLab endpoint: /webhooks/gitlab.
Start the Review Flow daemon
Launch the server as a background daemon. It will listen for webhook events and process review requests.
reviewflow startValidate the configuration
Run validate to check that all configuration is correct and the server can connect to your Git hosting platform.
reviewflow validateMonitor reviews via the dashboard
Open the real-time WebSocket dashboard to watch reviews in progress, see agent-by-agent progress, and review historical scores. Access it at the configured dashboard URL (default: http://localhost:3000).
# Check status and view logs
reviewflow status
reviewflow logsAutomated Code Review Examples
Client configuration
Example MCP server configuration for integrating Review Flow's MCP interface with Claude Desktop.
{
"mcpServers": {
"review-flow": {
"command": "npx",
"args": ["review-flow"],
"env": {}
}
}
}Prompts to try
CLI commands and prompts for working with Review Flow once it is running.
- "reviewflow status" — check if the daemon is running and how many reviews are queued
- "reviewflow logs" — stream live logs from the review daemon
- Open a GitHub PR and push a commit — Review Flow will automatically trigger a review
- "reviewflow stop" — gracefully stop the daemon when done
- Visit the dashboard to see per-agent scores for the latest review (Architecture, Security, Testing, Quality agents)Troubleshooting Automated Code Review
Webhooks from GitHub/GitLab are not reaching the server
Review Flow must be accessible from the internet to receive webhooks. Use a tunneling tool like ngrok ('ngrok http 3000') to expose your local server, then update the webhook URL in GitHub/GitLab settings to the ngrok URL. Verify the webhook secret matches what was set during 'reviewflow init'.
Reviews fail with 'claude command not found' or authentication errors
Ensure Claude Code CLI is installed ('npm install -g @anthropic-ai/claude-code') and authenticated ('claude login'). Review Flow invokes Claude Code in background mode (claude --bg) for each review session — the CLI must be on the system PATH accessible by the daemon.
Daemon fails to start or crashes immediately
Run 'reviewflow validate' to check configuration. Common causes: missing glab/gh CLI, insufficient git version, or configuration written to wrong path. Check logs with 'reviewflow logs'. The supervisor lock file is at ~/.reviewflow/supervisor.lock — delete it if the daemon is stuck and restart with 'reviewflow start'.
Frequently Asked Questions about Automated Code Review
What is Automated Code Review?
Automated Code Review is a Model Context Protocol (MCP) server that automated ai code reviews powered — webhook-driven, real-time dashboard, mcp integration, smart queue with deduplication, multi-agent audits, and iterative follow-up reviews for gitlab mrs and github prs It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Automated Code Review?
Follow the installation instructions on the Automated Code Review GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Automated Code Review?
Automated Code Review works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Automated Code Review free to use?
Yes, Automated Code Review is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Automated Code Review Alternatives — Similar Version Control Servers
Looking for alternatives to Automated Code Review? Here are other popular version control servers you can use with Claude, Cursor, and VS Code.
Ruiyu MA
★ 30.1kConnect AI assistants to GitHub - manage repos, issues, PRs, and workflows through natural language.
GitMCP
★ 8.1kTransforms any GitHub repository or GitHub Pages site into a documentation hub for AI assistants using the Model Context Protocol. It allows AI tools to access real-time code and documentation to prevent hallucinations and provide accurate API usage
GitHub Codemunch
★ 1.8kA token-efficient MCP server for exploring GitHub repositories using tree-sitter AST parsing to extract symbol signatures and summaries. It enables users to search and retrieve specific code components while significantly reducing token consumption c
Azure DevOps MCP Server
★ 1.7kThis server provides a convenient API for interacting with Azure DevOps services, enabling AI assistants and other tools to manage work items, code repositories, boards, sprints, and more. Built with the Model Context Protocol, it provides a standard
GitHub Official
★ 1.2kOfficial GitHub integration with comprehensive API coverage
Azure DevOps
★ 367Enables interaction with Azure DevOps through Cursor chat, providing tools to manage builds, pipelines, work items, sprints, and board operations. Supports secure authentication via Personal Access Tokens and allows natural language-driven DevOps tas
Browse More Version Control MCP Servers
Explore all version control servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Automated Code Review in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Automated Code Review?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.