OpenChrome
Open-source browser automation MCP server. Control your real Chrome from any AI agent.
What is OpenChrome?
OpenChrome is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to open-source browser automation mcp server. control your real chrome from any ai agent.
Open-source browser automation MCP server. Control your real Chrome from any AI agent.
This server falls under the Browser Automation category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Open-source browser automation MCP server. Control your real
Use Cases
Maintainer
Works with
Installation
NPM
npx -y openchrome-mcpManual Installation
npx -y openchrome-mcpConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use OpenChrome
OpenChrome is an open-source MCP server that gives AI agents direct control of a real Chrome browser using the Chrome DevTools Protocol, supporting parallel browsing sessions, form automation, DOM reading, performance profiling, and site monitoring. Unlike headless browser tools, it operates on your actual installed Chrome instance, preserving existing logins, cookies, and extensions so agents can access authenticated dashboards and member-only content immediately. With 118 available tools organized into navigation, reading, extraction, diagnostics, and async crawling categories, it is suitable for web scraping, UI testing, production debugging, and multi-step form automation.
Prerequisites
- Node.js 18+ installed
- Google Chrome installed on your machine (not Chromium — the real Chrome binary)
- Claude Desktop, Claude Code, or another MCP-compatible AI client
- npm access to install the openchrome-mcp package globally
Install the openchrome-mcp package globally
Install the OpenChrome MCP server binary globally via npm so the openchrome command is available on your PATH.
npm install -g openchrome-mcpRun the setup command for your MCP client
Run the appropriate setup command for your AI client. This automatically registers the server in the client's MCP configuration.
# For Claude Desktop / Claude Code
openchrome setup
# For Codex CLI
openchrome setup --client codex
# For OpenCode
npx openchrome-mcp setup --client opencodeVerify Chrome is detected
Run the doctor command to confirm OpenChrome can locate your Chrome installation, has disk access, and that the CDP port is available.
openchrome doctorConfigure manually for Cursor, VS Code, or Windsurf
For clients that do not have an automated setup command, add the following JSON block to your MCP client's config file manually.
Use Claude to automate Chrome
Ask Claude to navigate to a URL, read page content, fill a form, or capture performance metrics. Chrome will launch automatically on the first tool invocation when using --auto-launch.
OpenChrome Examples
Client configuration
Manual MCP config for Cursor, VS Code, Windsurf, or any client not covered by the openchrome setup command. The --auto-launch flag starts Chrome on first use.
{
"mcpServers": {
"openchrome": {
"command": "openchrome",
"args": ["serve", "--auto-launch"]
}
}
}Prompts to try
Use these prompts in Claude Desktop or Claude Code to drive Chrome through OpenChrome.
- "Compare AirPods Pro prices across Amazon, eBay, Walmart, and Best Buy simultaneously"
- "Navigate to my company dashboard at https://app.example.com and take a screenshot of the metrics page"
- "Fill out and submit the contact form at https://example.com/contact with these details: ..."
- "Capture Core Web Vitals (LCP, CLS) for https://example.com and report the results"
- "Crawl https://docs.example.com and extract all page titles and URLs"Troubleshooting OpenChrome
openchrome doctor reports Chrome binary not found
OpenChrome looks for the standard Chrome installation path. On macOS it expects Chrome at /Applications/Google Chrome.app. If Chrome is installed elsewhere, ensure the 'google-chrome' or 'google-chrome-stable' binary is on your PATH, or reinstall Chrome to the default location.
CDP port conflict: address already in use
Another Chrome instance is using the CDP port. Close all Chrome windows and any other tools using remote debugging, then restart OpenChrome. You can also check with 'lsof -i :9222' (macOS/Linux) to identify the conflicting process.
After updating openchrome-mcp, old tools or behaviors persist
Run 'npm install -g openchrome-mcp@latest' to update, then re-run 'openchrome setup' for your client to refresh the registration. The update command alone does not migrate existing host registrations.
Frequently Asked Questions about OpenChrome
What is OpenChrome?
OpenChrome is a Model Context Protocol (MCP) server that open-source browser automation mcp server. control your real chrome from any ai agent. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install OpenChrome?
Install via npm with the command: npx -y openchrome-mcp. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).
Which AI clients work with OpenChrome?
OpenChrome works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is OpenChrome free to use?
Yes, OpenChrome is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
OpenChrome Alternatives — Similar Browser Automation Servers
Looking for alternatives to OpenChrome? Here are other popular browser automation servers you can use with Claude, Cursor, and VS Code.
Chrome DevTools MCP
★ 40.6kAI-powered Chrome automation server with natural language element detection. Control Chrome browser through MCP protocol for testing, debugging, and performance analysis. Features 91% accuracy in element location, works with free AI models, and suppo
UI TARS Desktop
★ 34.9k📇 🏠 - Browser automation capabilities using Puppeteer, both support local and remote browser connection.
Playwright
★ 32.8kA production-ready browser automation server that enables AI assistants to interact with web pages using tools for navigation, element interaction, and data extraction. It features a built-in Inspector UI and robust crash recovery for reliable automa
Page Agent
★ 18.0kJavaScript in-page GUI agent. Control web interfaces with natural language.
Chrome
★ 11.7kAn extension-based MCP server that enables AI assistants to control your browser, leveraging existing sessions and login states for automation and content analysis. It provides over 20 tools for semantic tab search, interactive element manipulation,
LAMDA
★ 7.8kThe most powerful Android RPA agent framework, next generation mobile automation.
Browse More Browser Automation MCP Servers
Explore all browser automation servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up OpenChrome 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 OpenChrome?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.