Selenium

About

This powerful Model Context Protocol (MCP) server integrates Selenium WebDriver automation with AI assistants, allowing tools like Claude Desktop and Cursor AI to programmatically control web browsers. It facilitates web automation through natural language commands, making complex browser interactions accessible to AI-driven workflows and extending the capabilities of large language models to interact with the web.

Key Features

• Offers easy integration with any MCP-compatible AI client, including Cursor AI, Claude Desktop, and Google Gemini.
• Provides comprehensive session management including starting, listing, switching, and closing browser sessions.
• 0 GitHub stars
• Enables detailed element interaction such as finding, clicking, typing, hovering, dragging, and file uploads.
• Allows advanced actions like JavaScript execution, taking screenshots, and retrieving element text.
• Supports multi-browser automation (Chrome, Firefox) in headless or full mode.

Use Cases

• Allowing AI assistants to perform web-based research or data entry tasks.
• Enabling AI models to interact with and test web applications via natural language.
• Integrating web browser control into AI-driven workflow automation.