MCP Selenium Server

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

<a href="https://glama.ai/mcp/servers/@angiejones/mcp-selenium"> <img width="380" height="200" src="https://glama.ai/mcp/servers/@angiejones/mcp-selenium/badge" alt="Selenium MCP server" /> </a>

Setup

<details open> <summary><strong>Goose (Desktop)</strong></summary>

Paste into your browser address bar:

goose://extension?cmd=npx&arg=-y&arg=%40angiejones%2Fmcp-selenium%40latest&id=selenium-mcp&name=Selenium%20MCP&description=automates%20browser%20interactions

</details> <details> <summary><strong>Goose (CLI)</strong></summary>

goose session --with-extension "npx -y @angiejones/mcp-selenium@latest"

</details> <details> <summary><strong>Claude Code</strong></summary>

claude mcp add selenium -- npx -y @angiejones/mcp-selenium@latest

</details> <details> <summary><strong>Cursor / Windsurf / other MCP clients</strong></summary>

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

</details>

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.

---

<details> <summary><strong>Tools</strong></summary>

start_browser

Launches a browser session.

navigate

Navigates to a URL.

interact

Performs a mouse action on an element.

send_keys

Types text into an element. Clears the field first.

get_element_text

Gets the text content of an element.

get_element_attribute

Gets an attribute value from an element.

press_key

Presses a keyboard key.

upload_file

Uploads a file via a file input element.

take_screenshot

Captures a screenshot of the current page.

close_session

Closes the current browser session. No parameters.

execute_script

Executes JavaScript in the browser. Use for advanced interactions not covered by other tools (e.g., drag and drop, scrolling, reading computed styles, DOM manipulation).

window

Manages browser windows and tabs.

frame

Switches focus to a frame or back to the main page.

alert

Handles browser alert, confirm, or prompt dialogs.

add_cookie

Adds a cookie. Browser must be on a page from the cookie's domain.

get_cookies

Gets cookies. Returns all or a specific one by name.

delete_cookie

Deletes cookies. Deletes all or a specific one by name.

diagnostics

Gets browser diagnostics captured via WebDriver BiDi (auto-enabled when supported).

</details> <details> <summary><strong>Resources</strong></summary>

MCP resources provide read-only data that clients can access without calling a tool.

browser-status://current

Returns the current browser session status (active session ID or "no active session").

accessibility://current

Returns an accessibility tree snapshot of the current page — a compact, structured JSON representation of interactive elements and text content. Much smaller than full HTML. Useful for understanding page layout and finding elements to interact with.

</details>

---

<details> <summary><strong>Development</strong></summary>

Setup

git clone https://github.com/angiejones/mcp-selenium.git
cd mcp-selenium
npm install

Run Tests

npm test

Requires Chrome + chromedriver on PATH. Tests run headless.

Install via Smithery

npx -y @smithery/cli install @angiejones/mcp-selenium --client claude

Install globally

npm install -g @angiejones/mcp-selenium
mcp-selenium

</details>

License

MIT