mcp-browser-use

mcp-browser-use

4.2

If you are the rightful owner of mcp-browser-use and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcpreview.com.

AI-driven browser automation server implementing the Model Context Protocol (MCP) for natural language browser control and web research.

The browser-use MCP server and CLI is an AI-driven browser automation server that implements the Model Context Protocol (MCP) for natural language browser control and web research. It builds upon the browser-use/web-ui foundation, adapting core browser automation logic and configuration patterns. The server provides full protocol implementation for AI agent communication, enabling page navigation, form filling, and element interaction via natural language. It supports multi-LLM integration, including OpenAI, Anthropic, Azure, and others, and offers tools for deep web research and report generation. The server is configurable via environment variables and can connect to a user-launched Chrome/Chromium instance via the Chrome DevTools Protocol. Additionally, it provides a CLI for direct testing and scripting of its functionalities.

Features

  • MCP Integration - Full protocol implementation for AI agent communication.
  • Browser Automation - Page navigation, form filling, element interaction via natural language.
  • Visual Understanding - Optional screenshot analysis for vision-capable LLMs.
  • State Persistence - Manage a server browser session across multiple MCP calls or connect to user's browser.
  • Multi-LLM Support - Integrates with various LLM providers like OpenAI, Anthropic, Azure, and more.

Tools