Selenium

About

Selenium is a Model Context Protocol (MCP) server implementation built for Selenium WebDriver. It provides a standardized interface for browser automation, enabling MCP clients to interact with web browsers. The server supports a range of actions, including starting browser sessions, navigating URLs, finding and interacting with elements, handling mouse and keyboard events, taking screenshots, and uploading files. It supports both Chrome and Firefox, with options for headless mode, making it a versatile tool for web automation tasks.

Key Features

• Starts browser sessions with customizable options (headless, arguments).
• Finds elements using various locator strategies (id, css, xpath, name, tag, class).
• Performs actions like click, type, hover, drag and drop, and keyboard input.
• Takes screenshots of the current page.
• Supports file uploads.

Use Cases

• Automated web testing.
• Web scraping and data extraction.
• Automating repetitive browser-based tasks.