Skip to content
MCP server

Selenium Webdriver MCP

MCP server that lets AI assistants drive Selenium WebDriver browsers for testing

Runs locallyStatus and history
Install
Pricing
Open source
Platforms
API, CLI, vscode
Runs
Locally
Version
0.5.1
Listing updated
today

Similar MCP servers

About Selenium Webdriver MCP

Selenium Webdriver MCP is an open-source MCP server for browser automation. It runs locally on your machine and is started by your AI client.

The README describes this as a bridge between MCP clients and Selenium WebDriver. Once connected, an assistant can open Chrome, Firefox, Safari or Edge sessions and call browser actions such as navigating, clicking, typing, uploading files and taking screenshots, all exposed as named MCP tools.

The tool set is broad, grouped into browser management, cookies, window and frame switching, element interaction, scrolling and form handling. Elements can be located by id, CSS selector, XPath, name, tag or class. The project is written in TypeScript and validates inputs with Zod.

It suits developers and QA engineers who want an assistant to generate or run browser tests, or to pull data from pages. The README's example prompt asks an agent to register on a demo banking site and then produce page-object tests, which shows the intended workflow. The package is distributed on npm and is released under the MIT licence.

Install

Run in a terminal

claude mcp add selenium-webdriver-mcp --env YOUR_API_KEY='<YOUR_API_KEY>' -- npx -y selenium-webdriver-mcp

Add to claude_desktop_config.json

{
  "mcpServers": {
    "selenium-webdriver-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "selenium-webdriver-mcp"
      ],
      "env": {
        "YOUR_API_KEY": "<YOUR_API_KEY>"
      }
    }
  }
}

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "selenium-webdriver-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "selenium-webdriver-mcp"
      ],
      "env": {
        "YOUR_API_KEY": "<YOUR_API_KEY>"
      }
    }
  }
}

Add to .vscode/mcp.json

{
  "servers": {
    "selenium-webdriver-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "selenium-webdriver-mcp"
      ],
      "env": {
        "YOUR_API_KEY": "<YOUR_API_KEY>"
      }
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "selenium-webdriver-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "selenium-webdriver-mcp"
      ],
      "env": {
        "YOUR_API_KEY": "<YOUR_API_KEY>"
      }
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "selenium-webdriver-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "selenium-webdriver-mcp"
      ],
      "env": {
        "YOUR_API_KEY": "<YOUR_API_KEY>"
      }
    }
  }
}

Using several servers? Build one config file with the MCP config generator.

Configuration

  • YOUR_API_KEYYour API key for the service

Tools this server provides (6)

Taken from the project documentation; the running server may differ.

browser_open
Open a new browser session
browser_navigate
Navigate to a URL
browser_click
Click on an element
browser_type
Type text into an element
browser_screenshot
Take a screenshot
browser_execute_script
Execute JavaScript code

What it does

Multi-browser sessions
Opens automation sessions in Chrome, Firefox, Safari or Edge.
Element interaction tools
Covers clicking, typing, hovering, drag and drop and file uploads.
Cookie and window control
Reads, sets and deletes cookies and switches between browser windows and frames.
Multiple locator strategies
Finds elements by id, CSS, XPath, name, tag or class name.
Screenshots and scripts
Captures screenshots and runs JavaScript in the page.
Typed with Zod validation
Inputs are checked with Zod schemas in a TypeScript codebase.

Good for

  • Have an AI assistant generate browser test scripts for a web app
  • Automate a repetitive form submission or login flow through an agent
  • Extract page content or cookies during a scraping task
  • Capture screenshots of pages for visual review

Pricing

Open source

Free and open source under the MIT License.

Selenium Webdriver MCP FAQ

Which browsers are supported?

The README lists Chrome, Firefox, Safari and Edge, and says the browsers must be installed on the machine.

How is it installed?

The README gives an npx command using selenium-webdriver-mcp@latest, a global npm install, and a Smithery install option.

What license does it use?

The README states the project is released under the MIT License.

Is Selenium Webdriver MCP free?

Yes. Selenium Webdriver MCP is open source, so you can use and self-host it for free.

How do I add Selenium Webdriver MCP to Claude Code?

Run this command in your terminal: claude mcp add selenium-webdriver-mcp --env YOUR_API_KEY='<YOUR_API_KEY>' -- npx -y selenium-webdriver-mcp

What are the best alternatives to Selenium Webdriver MCP?

The closest alternatives to Selenium Webdriver MCP are Chrome DevTools MCP, MCP Browser Extension, MCP Browser, Cdpilot and Scrapling MCP Server.

Where this comes from

  • Description: written from the project's README and its MCP Registry entry.
  • Install steps: from the official MCP Registry entry.

How AIPoweredBot checks servers