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
AgentDeskAI/browser-tools-mcp
BrowserTools MCP is a sophisticated browser monitoring and interaction tool designed to enhance AI-powered applications by leveraging the Model Context Protocol (MCP). It integrates directly with MCP-compatible IDEs to capture, analyze, and interact with browser data through a Chrome extension and a local node server. This tool empowers developers and AI agents to perform comprehensive audits and debugging on web pages without leaving their development environment. The project consists of three main components: a Chrome extension that collects browser data such as screenshots, console logs, network activity, and DOM elements; a local node server that acts as middleware to gather and process logs; and the MCP server installed within the IDE that facilitates communication between the extension, the node server, and the IDE. This architecture allows seamless data flow and real-time interaction with the browser. BrowserTools MCP offers a suite of audit tools powered by Puppeteer and Lighthouse, enabling automated headless browser testing to evaluate web pages for accessibility (WCAG compliance), performance bottlenecks, SEO optimization, adherence to best practices, and NextJS-specific issues. These audits return structured JSON results that MCP-compatible clients can easily interpret and use to provide actionable insights. The tool includes features like Audit Mode and Debugger Mode, which run sequences of auditing and debugging tools respectively, enhancing the efficiency of web development and troubleshooting. The project also supports auto-pasting screenshots into AI coding agents like Cursor, improving workflow integration. With continuous updates addressing connectivity, usability, and feature enhancements, BrowserTools MCP is a powerful solution for developers seeking to integrate browser context awareness into AI-driven development environments, making web auditing and debugging more accessible and efficient.
https://github.com/AgentDeskAI/browser-tools-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.
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.
executeautomation/mcp-playwright
executeautomation/mcp-playwright is a Model Context Protocol server that enables AI-driven browser automation and web interactions using Playwright.