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
scrapeless-ai/scrapeless-mcp-server
Scrapeless MCP Server is the official Model Context Protocol integration for the Scrapeless web data platform, written in TypeScript. It gives MCP clients such as Claude Desktop, Cursor and Windsurf real-time access to the public web through three groups of tools. The first covers Google services: google_search acts as a general search engine over the results page, and google_trends returns trending search interest data. The second is a cloud browser controlled step by step: browser_create opens or reuses a hosted session, browser_goto, browser_go_back and browser_go_forward handle navigation, browser_click, browser_type, browser_press_key, browser_scroll and browser_scroll_to drive interaction, browser_wait and browser_wait_for handle timing, browser_screenshot, browser_get_html and browser_get_text read the page, and browser_close ends the session. Sessions can be watched live while the model works. The third group is direct scraping through the Scrapeless universal API, with scrape_html and scrape_markdown returning a rendered page in either format, which covers dynamic JavaScript-heavy sites that a plain fetch cannot read. The documented examples include retrieving content from pages protected by Cloudflare and writing extracted Markdown to a local file. Setup requires a Scrapeless account API key created in the dashboard. Two transports are supported: stdio, where the client runs npx scrapeless-mcp-server with SCRAPELESS_KEY in the environment, and streamable HTTP against the hosted endpoint at api.scrapeless.com/mcp with the key passed as an x-api-token header. Optional settings, given as environment variables in stdio mode or as HTTP headers in hosted mode, control the browser session: a reusable profile id for continuity, persistence of cookies and local storage, and a maximum session timeout in seconds. The server targets research assistants, coding copilots and autonomous agents that need live web data and interaction rather than static text.
https://github.com/scrapeless-ai/scrapeless-mcp-server
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.