angiejones/mcp-selenium

422 stars 0 forks 品質 92 トレンド 92

An MCP implementation for Selenium WebDriver

概要

A Model Context Protocol (MCP) server for Selenium WebDriver — browser automation for AI agents. Open Chrome, go to github.com/angiejones, and take a screenshot. The agent will call Selenium's APIs to start_browser, navigate, and take_screenshot. No manual scripting or explicit directions needed. Requires macOS. Run sudo safaridriver --enable once and enable "Allow Remote Automation" in Safari → Settings → Developer. No headless mode. Types text into an element. Clears the field first. Gets an attribute value from an element. Uploads a file via a file input element. Captures a screenshot of the current page.

README

MCP Selenium Server

A Model Context Protocol (MCP) server for Selenium WebDriver — browser automation for AI agents.

Setup

Example Usage

Tell the AI agent of your choice:

Open Chrome, go to github.com/angiejones, and take a screenshot.

The agent will call Selenium’s APIs to start_browser, navigate, and take_screenshot. No manual scripting or explicit directions needed.

Supported Browsers

Chrome, Firefox, Edge, and Safari.

Safari note: Requires macOS. Run sudo safaridriver --enable once and enable “Allow Remote Automation” in Safari → Settings → Developer. No headless mode.

License

MIT

View this README on GitHub

インストール

npx -y @angiejones/mcp-selenium@latest

設定

{
  "mcpServers": {
    "selenium": {
      "command": "npx",
      "args": ["-y", "@angiejones/mcp-selenium@latest"]
    }
  }
}