MCP Catalogs
← Home

open-browser-use

by iFurySt·★ 83·Score 46

Platform-neutral browser automation MCP server for AI agents with CLI and SDK support.

browser-automationdeveloper-toolsweb-scraping
12
Forks
0
Open issues
this month
Last commit
2d ago
Indexed

Overview

Open Browser Use is a browser automation layer that works across different AI agent runtimes. It provides Chrome automation capabilities through a combination of a browser extension and a CLI tool. The project exposes MCP server functionality that offers browser tools for tab management, navigation, CDP access, action planning, and cleanup. It supports multiple programming languages including JavaScript, Python, and Go through dedicated SDKs.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

you:Automated web testing and UI interactions for AI agents
you:Web scraping and data extraction using AI automation
you:Cross-platform browser automation without vendor lock-in
you:What browsers are supported?
you:How does it compare to Chrome Browser Use?

When to choose this

Choose this for Chrome-based browser automation in AI agents when you need an open-source solution with SDK support in multiple languages.

When NOT to choose this

Don't choose if you need browser automation for non-Chrome browsers or require more advanced browser control beyond basic tab and element interaction.

Tools this server exposes

7 tools extracted from the README
  • list_tabs

    List all browser tabs

  • open_tab

    Open a new browser tab

  • claim_tab

    Claim control of a browser tab

  • navigate

    Navigate to a URL in the current tab

  • cdp

    Execute Chrome DevTools Protocol commands

  • action_plan

    Execute a sequence of browser actions

  • cleanup

    Clean up browser resources and state

Note: Tool names were inferred from the description 'The server exposes browser tools for tab listing, opening, claiming, navigation, CDP, action plans, and cleanup.' without explicit documentation of their exact names or signatures.

Comparable tools

browserlesspuppeteerplaywrightselenium

Installation

Install the CLI globally:

npm i -g open-browser-use
open-browser-use setup

For MCP server integration:

npx add-mcp "obu mcp" --name open_browser_use --all -g -y

Manual configuration for Claude Desktop:

[mcp_servers.open_browser_use]
command = "obu"
args = ["mcp"]

FAQ

What browsers are supported?
Currently only Chrome is officially supported, though the architecture is designed to be browser-agnostic.
How does it compare to Chrome Browser Use?
It's an open-source alternative to the Chrome Browser Use capability in Codex.app, with no vendor lock-in and cross-platform support.

Compare open-browser-use with

open-browser-use vs ultimate_mcp_serveropen-browser-use vs mcp-server-chartopen-browser-use vs everythingopen-browser-use vs filesystemopen-browser-use vs time
GitHub →

Last updated · Auto-generated from public README + GitHub signals.