Open Browser Use
🔮 Platform-neutral Browser Use for AI agents: real Chrome automation with a CLI + SDKs, no lock-in, dead simple.
What is Open Browser Use?
Open Browser Use is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to 🔮 platform-neutral browser use for ai agents: real chrome automation with a cli + sdks, no lock-in, dead simple.
🔮 Platform-neutral Browser Use for AI agents: real Chrome automation with a CLI + SDKs, no lock-in, dead simple.
This server falls under the Browser Automation category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- 🔮 Platform-neutral Browser Use for AI agents: real Chrome au
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx open-browser-useConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Open Browser Use
Open Browser Use is a platform-neutral browser automation tool for AI agents that drives real Chrome via the Chrome DevTools Protocol — no Playwright, no Selenium, no vendor lock-in. It ships as a CLI, as JavaScript/TypeScript and Python SDKs, and as a Go package, all backed by a Chrome extension that acts as the native messaging host. Developers use it to give AI assistants real browser control for tasks like web scraping, UI testing, form filling, and multi-step web workflows, with the same setup working across Claude, Claude Code, and other MCP clients.
Prerequisites
- Node.js 18 or later (for the CLI and npm packages)
- Google Chrome browser installed
- The Open Browser Use Chrome extension (installed during setup)
- An MCP-compatible client such as Claude Desktop or Claude Code
Install the CLI globally
Install the open-browser-use CLI using npm or Homebrew (macOS/Linux).
npm i -g open-browser-use
# Or via Homebrew:
brew tap iFurySt/open-browser-use && brew install open-browser-useRun the setup wizard
The setup command registers the native messaging host and guides you through installing the Chrome extension. If automatic installation is unavailable, use the beta flag for manual extension installation.
open-browser-use setup
# Or for manual Chrome extension installation:
open-browser-use setup betaAdd the MCP server to your client
Register the Open Browser Use MCP server with your AI client. The obu mcp command starts the MCP server mode.
npx add-mcp "obu mcp" --name open_browser_use --all -g -yAdd as a Claude Code skill (optional)
If you use Claude Code, install the skill package for richer integration including slash commands.
npx skills add iFurySt/open-browser-use -g -a claude-code --skill open-browser-use -yVerify the extension is connected
Open Chrome and check that the Open Browser Use extension icon is visible and active. Then ask your AI client to list available browser tabs to confirm the connection.
Open Browser Use Examples
Client configuration
Manual configuration for Claude Desktop or Claude Code using the obu mcp server command.
{
"mcpServers": {
"open_browser_use": {
"command": "obu",
"args": ["mcp"]
}
}
}Prompts to try
Use natural language to automate Chrome browser tasks through your AI client.
- "Open https://news.ycombinator.com and summarize the top 5 posts"
- "Navigate to my GitHub notifications page and list unread items"
- "Fill out the contact form on example.com with test data and submit it"
- "Take a screenshot of the current active tab"
- "List all open browser tabs and close any that are YouTube"Troubleshooting Open Browser Use
The Chrome extension cannot communicate with the CLI native host
Re-run 'open-browser-use setup' to re-register the native messaging manifest. On macOS, make sure the CLI is installed in a standard PATH location like /usr/local/bin — not a nvm-managed path that Chrome cannot find.
MCP tools return 'no tabs available'
Make sure Chrome is open with at least one tab and the Open Browser Use extension is enabled and active (green icon). Extensions disabled via Chrome's Manage Extensions page will not respond.
obu command not found after npm install
Ensure npm global bin directory is in your PATH. Run 'npm bin -g' to find the directory and add it to your shell profile, then restart your terminal.
Frequently Asked Questions about Open Browser Use
What is Open Browser Use?
Open Browser Use is a Model Context Protocol (MCP) server that 🔮 platform-neutral browser use for ai agents: real chrome automation with a cli + sdks, no lock-in, dead simple. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Open Browser Use?
Follow the installation instructions on the Open Browser Use GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Open Browser Use?
Open Browser Use works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Open Browser Use free to use?
Yes, Open Browser Use is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Open Browser Use Alternatives — Similar Browser Automation Servers
Looking for alternatives to Open Browser Use? 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 Open Browser Use 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 Open Browser Use?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.