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
remorses/playwriter
Playwriter is an advanced Model Context Protocol (MCP) designed as a browser extension to enable efficient and powerful browser automation. It significantly reduces context window bloat by 90% compared to traditional Playwright MCP implementations and offers 10 times more capability by exposing the full Playwright API. This extension allows AI agents to control browser tabs directly within the user's existing Chrome browser environment, avoiding the need to launch separate browser instances. This approach facilitates collaboration between the user and AI, allowing the user to assist the AI with complex interactions such as captchas, and enables starting automation on existing pages to replicate bugs accurately. The Playwriter MCP extension integrates seamlessly with AI assistants by connecting through a relay server that communicates with enabled browser tabs. Users can install the extension from the Chrome Web Store, connect it to any tab, and configure their MCP client to use Playwriter. Once connected, the AI can control multiple tabs, switch contexts, create new tabs, and execute any Playwright code snippets, leveraging the full power of the Playwright API. Compared to other MCPs like Playwright MCP and BrowserMCP, Playwriter offers unique advantages such as reusing existing browser extensions, bypassing automation detection by toggling the extension connection, and reducing resource consumption by not spawning new browser instances. Unlike BrowserMCP and Antigravity (Jetski), which expose multiple discrete tools for browser actions, Playwriter uses a single "execute" tool that sends Playwright code snippets, reducing context window usage and latency while increasing capability. The architecture consists of a browser extension running in Chrome, a local WebSocket relay server, and an MCP client (such as Claude Desktop) that communicates with the extension to perform browser automation tasks. This design ensures low latency, high efficiency, and full access to Playwright's capabilities, making Playwriter a superior choice for AI-driven browser automation within the MCP ecosystem.
https://github.com/remorses/playwriter
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.