browser-use/browser-use
Open-source browser automation agent for LLMs, usable as a Python library, CLI, hosted cloud service, or MCP server exposing browser-control tools.
Awesome MCP › Browser Automation
microsoft/playwright-mcp
Playwright MCP is a Model Context Protocol (MCP) server designed to enable large language models (LLMs) to automate and interact with web browsers efficiently and deterministically. It leverages Playwright's accessibility tree to provide structured accessibility snapshots, allowing LLMs to interact with web pages without relying on pixel-based inputs or vision models. This approach bypasses the need for screenshots or visually-tuned models, making the automation process faster, lightweight, and more reliable. The server supports various browsers including Chrome, Firefox, WebKit, and Microsoft Edge, and offers a range of configurable options such as blocking or allowing specific origins, running in headless mode, emulating devices, and specifying user agents. It can be integrated with multiple MCP clients like VS Code, Cursor, Windsurf, Claude Desktop, Claude Code, and Qodo Gen, making it versatile for different development environments. Playwright MCP supports persistent user profiles to maintain logged-in states across sessions or isolated contexts for testing purposes. It also provides capabilities like saving Playwright traces, managing storage states, and configuring proxy servers. The server is designed to be LLM-friendly by operating purely on structured data, avoiding the ambiguity common with screenshot-based browser automation methods. Installation is straightforward using npm or through MCP client configurations, and the server can be easily added to various tools via simple commands or configuration files. This makes Playwright MCP a powerful tool for developers and researchers looking to harness the power of LLMs for browser automation tasks in a deterministic and efficient manner.
https://github.com/microsoft/playwright-mcp
Also in Browser Automation
unclecode/crawl4ai
Open-source async web crawler and scraper that converts websites into clean, LLM-ready Markdown for RAG pipelines and AI agents, with an official MCP server for AI assistants.
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).
browser-use/browser-harness
MCP-compatible harness that lets coding agents drive a user's real, logged-in Chrome browser over the DevTools Protocol, writing new helper scripts as it works.
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.
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.