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
eyalzh/browser-control-mcp
browser-control-mcp is a Model Context Protocol server bundled with a Firefox browser extension that lets an AI assistant work with the user's own browser rather than a separate automation instance. The server exposes tools to open and close tabs, list open tabs, create named and coloured tab groups, reorder tabs, read and search browsing history, read a web page's text content and links, and find and highlight text in a tab. The last two require the user's explicit consent in the browser for each domain. Typical uses described in the README include closing unrelated tabs, grouping development tabs, reopening articles found in history, reading a story together with its comments, or opening several search results and summarising them into a table. The project positions itself as a more restricted alternative to general web automation MCP servers, and the security model is the main design point. It cannot modify pages, interact with page elements or run arbitrary scripts. Per-domain content consent is enforced at the extension manifest level. The extension and server communicate over a local-only connection protected by a shared secret, there is no remote data collection or tracking, and the extension keeps an audit log of tool calls plus per-tool enable and disable settings and carries no runtime third-party dependencies. The README still labels the project experimental and advises monitoring tool calls carefully. Installation has two paths: the published add-on on addons.mozilla.org together with a Claude Desktop DXT extension file, or a build from source with npm install and npm run build followed by loading the extension as a temporary add-on from about:debugging. The MCP server is then registered in the client configuration with EXTENSION_SECRET copied from the extension preferences page and an optional EXTENSION_PORT, defaulting to 8089. A Docker-based server configuration is also documented.
https://github.com/eyalzh/browser-control-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.