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
OTA-Tech-AI/web-agent-protocol
The Web Agent Protocol (WAP) is a standardized framework designed to facilitate the recording and replaying of user interactions within web browsers, with integrated support for the Model Context Protocol (MCP). This framework enables efficient automation and reuse of browser actions by separating the concerns of action recording and execution. WAP provides a comprehensive Python SDK that implements the full specification, allowing users to collect user interaction data through a dedicated Chrome extension, convert raw event streams into exact or smart replay action lists, and transform these recorded actions into MCP servers for reuse by any agent or user. The replay functionality ensures accurate browser operations by using the WAP-Replay protocol. The project includes tools for recording user interactions via a Chrome extension, a backend server to collect and store interaction data, and scripts to generate replay lists in different modes. Users can replay recorded actions either directly or through MCP servers, enabling flexible and reusable automation workflows. Additionally, the project offers a desktop application for easy replay of action lists without complex setup. The framework supports goal-oriented smart replay, which condenses user actions into efficient steps, and exact replay, which reproduces every action precisely. The project is well-documented with setup instructions, usage examples, and troubleshooting tips. It also acknowledges dependencies on other projects such as Browser-Use, MCP Python SDK, and DOMListenerExtension. Overall, WAP is a powerful tool for automating browser interactions, enhancing productivity, and enabling advanced reuse of recorded web actions through MCP integration.
https://github.com/OTA-Tech-AI/web-agent-protocol
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.