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
browser-use/vibetest-use
Vibetest MCP is an automated quality assurance (QA) testing tool designed to work within the Model Context Protocol (MCP) framework. It leverages Browser-Use agents to perform comprehensive testing on vibe-coded websites, focusing on detecting UI bugs, broken links, accessibility issues, and other technical problems. The tool is capable of testing both live websites and local development environments, making it versatile for developers and QA teams. The project includes an MCP server that can launch multiple Browser-Use agents simultaneously to conduct thorough testing. Users can specify parameters such as the URL to test, the number of agents to deploy for testing, and whether to run the tests in headless mode or not. This flexibility allows for scalable and customizable testing scenarios depending on the complexity and requirements of the website. Vibetest MCP integrates with Claude Code and Cursor, two platforms that support MCP, enabling easy addition and management of the MCP server through CLI commands or UI settings. The tool requires Python 3.11 or higher and a Google API key to function, supporting advanced features like gemini-2.0-flash. The project is well-documented with quick start instructions, including installation steps, configuration examples, and usage prompts. It is licensed under the MIT license and is powered by the Browser Use project, which provides the underlying agent technology. Overall, Vibetest MCP offers an automated, scalable, and efficient solution for ensuring the quality and accessibility of vibe-coded websites by leveraging the MCP framework and Browser-Use agents.
https://github.com/browser-use/vibetest-use
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.