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
jae-jae/fetcher-mcp
Fetcher MCP is a Model Context Protocol (MCP) server designed to fetch and intelligently extract web page content using the Playwright headless browser. It supports JavaScript execution, enabling it to handle dynamic web content and modern web applications that rely heavily on client-side scripting. The server uses a built-in Readability algorithm to automatically extract the main content from web pages, filtering out ads, navigation bars, and other non-essential elements, which makes the extracted data cleaner and more useful for downstream applications. Fetcher MCP supports flexible output formats, including HTML and Markdown, allowing easy integration with various systems and workflows. It also features parallel processing capabilities through its `fetch_urls` tool, which can concurrently fetch multiple URLs, significantly improving efficiency for batch operations. To optimize resource usage, the server automatically blocks unnecessary resources such as images, stylesheets, fonts, and media, reducing bandwidth consumption and improving performance. The server offers robust error handling and logging to ensure reliable operation even when dealing with problematic or complex web pages. Users can configure various parameters such as timeouts, content extraction preferences, output formatting, and debugging options to tailor the fetching process to specific needs. Debug mode allows users to view the browser window for troubleshooting or manual interaction, such as logging into websites that require authentication. Fetcher MCP supports both modern Streamable HTTP and legacy Server-Sent Events (SSE) endpoints for communication, providing flexibility in client integration. It can be easily deployed using Docker or Docker Compose, facilitating scalable and consistent deployment environments. Overall, Fetcher MCP is a powerful and flexible MCP server that leverages Playwright to provide advanced web content fetching and extraction capabilities, making it suitable for applications that require dynamic content handling, intelligent extraction, and efficient batch processing.
https://github.com/jae-jae/fetcher-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.
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.