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
blackwhite084/playwright-plus-python-mcp
The project "playwright-plus-python-mcp" is a Model Context Protocol (MCP) server that integrates Playwright tools to facilitate web automation, note management, and programmable web interactions within the MCP ecosystem. This server provides a robust set of tools and resources designed to interact with web pages programmatically, enabling automated navigation, interaction, and content retrieval. Key features include a simple note storage system accessible via a custom note:// URI scheme, where each note resource contains a name, description, and plain text content. The server offers a prompt called "summarize-notes" that generates summaries of all stored notes, with an optional style argument to control the level of detail in the summary. The server implements several Playwright-based tools: - `playwright_navigate` to navigate to specified URLs, automatically creating new sessions if none are active. - `playwright_screenshot` to capture screenshots of entire pages or specific elements identified by CSS selectors. - `playwright_click` and `playwright_click_text` to simulate clicking elements by CSS selector or text content. - `playwright_fill` to fill input fields with specified values. - `playwright_evaluate` to execute arbitrary JavaScript code within the browser context. - `playwright_get_text_content` and `playwright_get_html_content` to retrieve visible text or HTML content from pages or specific elements. The project includes detailed instructions for installation, configuration, development, building, publishing, and debugging, emphasizing the use of the MCP Inspector for enhanced debugging experiences. It supports both development/unpublished and published server configurations. Overall, this MCP server extends the capabilities of the MCP ecosystem by integrating powerful web automation tools, enabling users to programmatically interact with web content, manage notes, and automate web tasks efficiently.
https://github.com/blackwhite084/playwright-plus-python-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.