microsoft/playwright-mcp
Playwright MCP is an MCP server that enables LLMs to automate and interact with web browsers using structured accessibility snapshots for efficient and deterministic browser automation.
Awesome MCP › Browser Automation
co-browser/browser-use-mcp-server
The project "browser-use-mcp-server" is an MCP (Model Context Protocol) server designed to enable AI agents to control web browsers through browser automation. It leverages the browser-use library and supports multiple transport protocols, including SSE (Server-Sent Events) and stdio, allowing flexible communication methods between clients and the server. The server also features real-time VNC streaming, which enables users to watch the browser automation process live, providing transparency and monitoring capabilities. The server is built with prerequisites such as the uv Python package manager, Playwright for browser automation, and mcp-proxy for stdio mode. It supports asynchronous task execution, allowing browser operations to be performed without blocking other processes. The project provides detailed instructions for installation, environment setup, and usage in both SSE and stdio modes, making it accessible for developers to integrate and deploy. Client configuration examples are provided for both transport modes, with specific configuration paths for popular clients like Cursor, Windsurf, and Claude. The project also supports local development with instructions for building, installing, and running the server locally. Additionally, a Docker setup is available for consistent and isolated deployment, including options for setting custom VNC passwords for secure access. The server is designed to facilitate AI-driven browser automation tasks, such as opening web pages and extracting information, demonstrated by an example where an AI agent retrieves the top-ranked article from a news website. The project is actively maintained and supported, with community engagement through Twitter and Discord, and it provides a star history chart indicating its popularity and growth. Overall, browser-use-mcp-server is a robust and versatile MCP server that empowers AI agents to interact with web browsers efficiently, supporting multiple communication protocols and real-time monitoring through VNC streaming.
https://github.com/co-browser/browser-use-mcp-server
Also in Browser Automation
alibaba/page-agent
Page Agent is an in-page JavaScript GUI agent that enables natural language control of web interfaces, offering easy integration without browser extensions or headless browsers.
Skyvern-AI/skyvern
Skyvern automates browser-based workflows using large language models and computer vision, providing a robust and scalable web automation solution that integrates with the Model Context Protocol (MCP).
firecrawl/firecrawl-mcp-server
Firecrawl MCP Server is an MCP server implementation that adds advanced web scraping, crawling, and search capabilities to LLM clients like Cursor and Claude, enabling enhanced data extraction and research functionalities.
AgentDeskAI/browser-tools-mcp
BrowserTools MCP is a powerful browser monitoring and interaction tool that leverages the Model Context Protocol to enable AI-powered applications to capture and analyze browser data directly within MCP-compatible IDEs.
BrowserMCP/mcp
Browser MCP is an MCP server and Chrome extension that enables AI applications to automate and control your browser locally using your existing browser profile for privacy, speed, and stealth.
apify/actors-mcp-server
Apify MCP Server is an MCP protocol server implementation that enables AI assistants to interact with Apify Actors for data extraction, web scraping, and automation tasks through a standardized protocol.
agent-infra/sandbox
agent-infra/sandbox is an all-in-one sandbox environment combining Browser, Shell, File, MCP, and VSCode Server in a single Docker container, providing a unified, secure, and agent-ready platform for AI agent development and testing.