Automated Code Review

v1.0.0Version Controlstable

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

aiautomationclaudeclean-architecturecode-review
Share:
37
Stars
0
Downloads
0
Weekly
0/5

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

PR and MR code review automation
Real-time review dashboard
Multi-agent audits
DGouron

Maintainer

LicenseMIT
Languagetypescript
Versionv1.0.0
UpdatedMay 20, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx review-flow

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

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
1

Install Review Flow globally

Install the reviewflow CLI package globally via npm.

npm install -g reviewflow
2

Run the interactive setup wizard

The init command walks you through configuring your GitHub/GitLab connection, webhook secrets, Claude Code integration, and dashboard settings.

reviewflow init
3

Configure 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.

4

Start the Review Flow daemon

Launch the server as a background daemon. It will listen for webhook events and process review requests.

reviewflow start
5

Validate the configuration

Run validate to check that all configuration is correct and the server can connect to your Git hosting platform.

reviewflow validate
6

Monitor 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 logs

Automated 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.

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.

Quick Config Preview

{ "mcpServers": { "review-flow": { "command": "npx", "args": ["-y", "review-flow"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

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.

33,000+ ServersFree & Open SourceStep-by-Step Guides