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
hyperbrowserai/mcp
Hyperbrowser MCP Server is an implementation of the Model Context Protocol (MCP) designed to facilitate web scraping, data extraction, and browser automation through AI agents and browser automation techniques. The server offers a suite of tools that enable users to scrape and extract structured data from webpages, crawl multiple linked pages, and perform web searches using Bing. It supports various browser agents including OpenAI's Computer Use Agent (CUA), Anthropic's Claude Computer Use, and a lightweight Browser Use agent, allowing for flexible and powerful automation capabilities. The server can be installed manually via npm using an API key and is compatible with platforms like Cursor and Windsurf, where it can be configured to run seamlessly. For development, the source code is available for cloning, building, and running directly. The project also provides example configurations for integration with clients such as the Claude Desktop app. Key tools include scraping webpages to extract formatted content such as markdown and screenshots, crawling webpages to gather LLM-friendly content, converting unstructured HTML into structured JSON data, and performing web searches. Additionally, it supports profile management for persistent Hyperbrowser profiles, enabling creation, deletion, and listing of profiles. The server also offers resource discovery methods to provide documentation about Hyperbrowser, enhancing client usability. Licensed under the MIT License, the Hyperbrowser MCP Server is a robust and extensible platform for leveraging AI-driven browser automation and data extraction within the Model Context Protocol framework. More information about the Hyperbrowser and MCP can be found on their respective documentation sites.
https://github.com/hyperbrowserai/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.
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.
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.