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
refreshdotdev/web-eval-agent
The project "refreshdotdev/web-eval-agent" is an MCP (Model Context Protocol) server designed to autonomously evaluate web applications. It acts as an automated UX evaluator that drives a browser to navigate through web apps, capturing screenshots, console logs, network traffic, and generating detailed UX reports. The server leverages BrowserUse technology for efficient navigation and integrates with the operative.sh MCP backend for enhanced performance. Key features include autonomous debugging where the Cursor agent tests the code it wrote end-to-end, capturing console errors and network requests intelligently filtered into the context window. The project provides two main tools: "web_eval_agent" for automated UX evaluation and "setup_browser_state" for opening an interactive browser session to save authentication states for reuse. Users can trigger these tools directly from their IDE chat interface, making it convenient to test web applications by simply sending natural language commands. The project supports easy setup with one-click integration via an API key from operative.sh, and manual installation instructions are provided for macOS, Linux, and Windows environments. It uses Playwright for browser automation and UV for running the MCP server. Despite its powerful capabilities, the project has been sunset and discontinued, with the team working on a new solution at withrefresh.com. The repository includes detailed documentation on installation, usage, updating, and troubleshooting, along with example output reports demonstrating the agent's evaluation process. This project is highly relevant for developers looking to automate web application testing and debugging within their development environment using MCP protocols.
https://github.com/refreshdotdev/web-eval-agent
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.