cline-browser-use-mcp

cline-browser-use-mcp

17
browser_automation

Browser Use Server is a Model Context Protocol server designed for browser automation. It allows operations such as taking webpage screenshots, retrieving HTML, executing JavaScript, and fetching console logs, with support for custom interaction steps. It is suitable for tasks that require complex browser interactions and automation.

Browser Use Server

  • A Model Context Protocol server focused on browser automation using Python scripts.
  • Key features include capturing webpage screenshots, retrieving HTML content, executing JavaScript on webpages, and obtaining console logs.
  • Supports custom interaction steps post page load for operations like clicking elements or scrolling.

Features

  • Browser Operations
    • Screenshot capture
    • HTML retrieval
    • JavaScript execution
    • Console log retrieval
  • Prerequisites
    • Install Xvfb for headless automation.
    • Use Miniconda or Anaconda for environment setup and dependency management.
    • Configure API keys for various LLM providers.

Installation

  • Install using Smithery: Clone repository and install dependencies.
  • Build server with npm run build.

Usage

  • Execute server using Node.js, accessible via stdio.
  • Perform tasks like multi-step automation and DOM manipulation.