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
BrowserMCP/mcp
Browser MCP is a Model Context Provider (MCP) server combined with a Chrome extension designed to enable AI applications to automate and control the user's browser locally. This project focuses on providing a seamless and private automation experience by leveraging the user's existing browser profile, which allows the AI to interact with the browser as if it were a human user. This approach ensures that the automation is fast, private, and stealthy. The automation happens entirely on the user's machine, eliminating network latency and enhancing performance. Privacy is a key feature since all browser activities remain local and are not transmitted to any remote servers. By using the real browser fingerprint and the existing logged-in sessions, Browser MCP avoids common bot detection mechanisms and CAPTCHAs, which are typical hurdles in automated browser interactions. The project supports integration with AI applications such as VS Code, Claude, Cursor, and Windsurf, enabling these tools to automate browser tasks effectively. The repository contains the core MCP code for Browser MCP but currently depends on other components from a monorepo for full functionality. Browser MCP was adapted from the Playwright MCP server, shifting from creating new browser instances to automating the user's existing browser, which is a significant advantage for maintaining logged-in states and avoiding detection. Overall, Browser MCP is a powerful tool for developers and AI applications that require browser automation with an emphasis on privacy, speed, and stealth, making it suitable for advanced AI-driven workflows that interact with web environments in a human-like manner.
https://github.com/BrowserMCP/mcp
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.
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.
executeautomation/mcp-playwright
executeautomation/mcp-playwright is a Model Context Protocol server that enables AI-driven browser automation and web interactions using Playwright.