MCP Selenium Server

A Model Context Protocol (MCP) server implementation for Selenium WebDriver, enabling browser automation through standardized MCP clients.

Video Demo (Click to Watch)

Features

Start browser sessions with customizable options
Navigate to URLs
Find elements using various locator strategies
Click, type, and interact with elements
Perform mouse actions (hover, drag and drop)
Handle keyboard input
Take screenshots
Upload files
Support for headless mode

Supported Browsers

Chrome
Firefox
MS Edge

Use with Goose

Option 1: One-click install

Copy and paste the link below into a browser address bar to add this extension to goose desktop:

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

Option 2: Add manually to desktop or CLI

Name: Selenium MCP
Description: automates browser interactions
Command: npx -y @angiejones/mcp-selenium

Use with other MCP clients (e.g. Claude Desktop, etc)

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

Development

To work on this project:

Clone the repository
Install dependencies: npm install
Run the server: npm start

Installation

Installing via Smithery

To install MCP Selenium for Claude Desktop automatically via Smithery:

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

Manual Installation

npm install -g @angiejones/mcp-selenium

Usage

Start the server by running:

mcp-selenium

Or use with NPX in your MCP configuration:

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

Tools

start_browser

Launches a browser session.

Parameters:

browser (required): Browser to launch
- Type: string
- Enum: ["chrome", "firefox"]
options: Browser configuration options
- Type: object
- Properties:
  - headless: Run browser in headless mode
    - Type: boolean
  - arguments: Additional browser arguments
    - Type: array of strings

Example:

{
  "tool": "start_browser",
  "parameters": {
    "browser": "chrome",
    "options": {
      "headless": true,
      "arguments": ["--no-sandbox"]
    }
  }
}

navigate

Navigates to a URL.

Parameters:

url (required): URL to navigate to
- Type: string

Example:

{
  "tool": "navigate",
  "parameters": {
    "url": "https://www.example.com"
  }
}

find_element

Finds an element on the page.

Parameters:

by (required): Locator strategy
- Type: string
- Enum: ["id", "css", "xpath", "name", "tag", "class"]
value (required): Value for the locator strategy
- Type: string
timeout: Maximum time to wait for element in milliseconds
- Type: number
- Default: 10000

Example:

{
  "tool": "find_element",
  "parameters": {
    "by": "id",
    "value": "search-input",
    "timeout": 5000
  }
}

click_element

Clicks an element.

Parameters:

by (required): Locator strategy
- Type: string
- Enum: ["id", "css", "xpath", "name", "tag", "class"]
value (required): Value for the locator strategy
- Type: string
timeout: Maximum time to wait for element in milliseconds
- Type: number
- Default: 10000

Example:

{
  "tool": "click_element",
  "parameters": {
    "by": "css",
    "value": ".submit-button"
  }
}

send_keys

Sends keys to an element (typing).

Parameters:

by (required): Locator strategy
- Type: string
- Enum: ["id", "css", "xpath", "name", "tag", "class"]
value (required): Value for the locator strategy
- Type: string
text (required): Text to enter into the element
- Type: string
timeout: Maximum time to wait for element in milliseconds
- Type: number
- Default: 10000

Example:

{
  "tool": "send_keys",
  "parameters": {
    "by": "name",
    "value": "username",
    "text": "testuser"
  }
}

get_element_text

Gets the text() of an element.

Parameters:

by (required): Locator strategy
- Type: string
- Enum: ["id", "css", "xpath", "name", "tag", "class"]
value (required): Value for the locator strategy
- Type: string
timeout: Maximum time to wait for element in milliseconds
- Type: number
- Default: 10000

Example:

{
  "tool": "get_element_text",
  "parameters": {
    "by": "css",
    "value": ".message"
  }
}

hover

Moves the mouse to hover over an element.

Parameters:

by (required): Locator strategy
- Type: string
- Enum: ["id", "css", "xpath", "name", "tag", "class"]
value (required): Value for the locator strategy
- Type: string
timeout: Maximum time to wait for element in milliseconds
- Type: number
- Default: 10000

Example:

{
  "tool": "hover",
  "parameters": {
    "by": "css",
    "value": ".dropdown-menu"
  }
}

drag_and_drop

Drags an element and drops it onto another element.

Parameters:

by (required): Locator strategy for source element
- Type: string
- Enum: ["id", "css", "xpath", "name", "tag", "class"]
value (required): Value for the source locator strategy
- Type: string
targetBy (required): Locator strategy for target element
- Type: string
- Enum: ["id", "css", "xpath", "name", "tag", "class"]
targetValue (required): Value for the target locator strategy
- Type: string
timeout: Maximum time to wait for elements in milliseconds
- Type: number
- Default: 10000

Example:

{
  "tool": "drag_and_drop",
  "parameters": {
    "by": "id",
    "value": "draggable",
    "targetBy": "id",
    "targetValue": "droppable"
  }
}

double_click

Performs a double click on an element.

Parameters:

by (required): Locator strategy
- Type: string
- Enum: ["id", "css", "xpath", "name", "tag", "class"]
value (required): Value for the locator strategy
- Type: string
timeout: Maximum time to wait for element in milliseconds
- Type: number
- Default: 10000

Example:

{
  "tool": "double_click",
  "parameters": {
    "by": "css",
    "value": ".editable-text"
  }
}

right_click

Performs a right click (context click) on an element.

Parameters:

by (required): Locator strategy
- Type: string
- Enum: ["id", "css", "xpath", "name", "tag", "class"]
value (required): Value for the locator strategy
- Type: string
timeout: Maximum time to wait for element in milliseconds
- Type: number
- Default: 10000

Example:

{
  "tool": "right_click",
  "parameters": {
    "by": "css",
    "value": ".context-menu-trigger"
  }
}

press_key

Simulates pressing a keyboard key.

Parameters:

key (required): Key to press (e.g., 'Enter', 'Tab', 'a', etc.)
- Type: string

Example:

{
  "tool": "press_key",
  "parameters": {
    "key": "Enter"
  }
}

upload_file

Uploads a file using a file input element.

Parameters:

by (required): Locator strategy
- Type: string
- Enum: ["id", "css", "xpath", "name", "tag", "class"]
value (required): Value for the locator strategy
- Type: string
filePath (required): Absolute path to the file to upload
- Type: string
timeout: Maximum time to wait for element in milliseconds
- Type: number
- Default: 10000

Example:

{
  "tool": "upload_file",
  "parameters": {
    "by": "id",
    "value": "file-input",
    "filePath": "/path/to/file.pdf"
  }
}

take_screenshot

Captures a screenshot of the current page.

Parameters:

outputPath (optional): Path where to save the screenshot. If not provided, returns base64 data.
- Type: string

Example:

{
  "tool": "take_screenshot",
  "parameters": {
    "outputPath": "/path/to/screenshot.png"
  }
}

close_session

Closes the current browser session and cleans up resources.

Parameters: None required

Example:

{
  "tool": "close_session",
  "parameters": {}
}

License

MIT

This server cannot be installed

security - not tested

license - permissive license

quality - not tested

How are these scores calculated?

A Model Context Protocol server implementation that enables browser automation through standardized MCP clients, supporting features like navigation, element interaction, and screenshots across Chrome, Firefox, and Edge browsers.

Related MCP Servers

BrowserCat MCP Server (Browser Automation)official
browsercat
-
security
F
license
-
quality
A Model Context Protocol server that provides browser automation capabilities using BrowserCat's cloud browser service. This server enables LLMs to interact with web pages, take screenshots, and execute JavaScript in a real browser environment without needing to install browsers locally.
Last updated -
20
2
Playwright MCP Server
pvinis
A
security
A
license
A
quality
A Model Context Protocol server that enables LLMs to interact with web pages, take screenshots, generate test code, scrape web pages, and execute JavaScript in a real browser environment.
Last updated -
29
69
9
TypeScript
MIT License
Chrome Debug MCP Server
Rainmen-xia
A
security
A
license
A
quality
A Model Context Protocol server that connects to Chrome debugging ports, enabling browser automation with persistent login sessions.
Last updated -
10
338
7
JavaScript
MIT License
Snowfort Circuit MCPofficial
snowfort-ai
-
security
F
license
-
quality
A comprehensive Model Context Protocol (MCP) server suite that enables AI coding agents to automate both web browsers and Electron desktop applications with auto-snapshots and element references.
Last updated -
31
TypeScript

View all related MCP servers

MCP Selenium Server