Loading connector details…
Loading connector details…
Choose a unique username to continue using AgentHotspot
by angiejones • Frontend & UI
An MCP server that exposes Selenium WebDriver functionality so agents can automate browsers via standardized MCP clients.
Perform end-to-end browser automation (navigate pages, click, type, and submit forms) to complete web-based tasks.
Extract page content or element text and take screenshots from dynamic websites using a real browser context.
Interact with complex UI widgets (drag-and-drop, hover menus, file uploads, keyboard/mouse actions) that require a full browser environment.
This project implements a Model Context Protocol (MCP) server around Selenium WebDriver, allowing agents to start browser sessions, navigate pages, find and interact with elements, perform mouse and keyboard actions, upload files, and take screenshots. It supports Chrome, Firefox, and Microsoft Edge with options for headless mode and custom browser arguments. The server is distributed as an npm package and can be run via npx or installed globally, making it easy to integrate with MCP-capable agents and desktop clients.
launches browser
navigates to a URL
performs a mouse action on an element
sends keys to an element, aka typing. Clears the field first.
gets the text content of an element
Current browser session status
Accessibility tree snapshot of the current page. A compact, structured representation of interactive elements and text content, much smaller than full HTML. Useful for understanding page layout and finding elements to interact with.
Scores are informational only and provided “as is” without warranty. AgentHotspot assumes no liability for actions taken based on these ratings.