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
browser-use/browser-harness
Browser Harness lets coding agents such as Claude Code, Codex or Cursor control a user's actual running Chrome browser, already logged into the user's own accounts, instead of a fresh and unauthenticated browser instance. It connects over the Chrome DevTools Protocol after the user enables remote debugging, and setup is a single prompt pasted into the coding agent, which installs the tool, registers a skill describing the browser workflow, and connects to the running browser. Its defining design choice is that the agent extends the harness itself: when it meets a missing capability, such as uploading a file, it writes a new Python helper into a local workspace file, so the tool accumulates task-specific automation over time while its protected core code stays untouched. This functionality is exposed to any MCP client through a `browser-harness-mcp` server, and the project's documentation explicitly contrasts its approach with Playwright MCP: Playwright MCP by default automates its own isolated browser profile, with opt-in extension or CDP-endpoint modes to reach a real Chrome, whereas Browser Harness is built from the start around driving the user's whole real Chrome, with the user approving the connection once through `chrome://inspect`. It is open source under the MIT license, maintained by the team behind the broader `browser-use` agent library, and is aimed at letting a coding agent handle complete browser-based tasks, such as downloading files, filling in logged-in forms, or reading personalized pages, without the user manually driving the browser on the agent's behalf.
https://github.com/browser-use/browser-harness
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).
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.