A
security-
licenseA
qualityA MCP server that provides browser automation tools, allowing users to navigate websites, take screenshots, click elements, fill forms, and execute JavaScript through Playwright.
Last updated -
8
1
Apache 2.0
Supports launching and controlling Firefox browser sessions with customizable options through Selenium WebDriver.
Allows AI agents to control web browsers through the Selenium WebDriver. Supports starting browser sessions, navigating to URLs, finding elements, clicking, typing, and performing various mouse and keyboard actions.
MCP Selenium Server
A Model Context Protocol (MCP) server implementation for Selenium WebDriver, enabling browser automation through standardized MCP clients.
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
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 MCPDescription:
automates browser interactionsCommand:
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 installRun 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 launchType: string
Enum: ["chrome", "firefox"]
options: Browser configuration optionsType: object
Properties:
headless: Run browser in headless modeType: boolean
arguments: Additional browser argumentsType: 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 toType: string
Example:
{
"tool": "navigate",
"parameters": {
"url": "https://www.example.com"
}
}
find_element
Finds an element on the page.
Parameters:
by(required): Locator strategyType: string
Enum: ["id", "css", "xpath", "name", "tag", "class"]
value(required): Value for the locator strategyType: string
timeout: Maximum time to wait for element in millisecondsType: number
Default: 10000
Example:
{
"tool": "find_element",
"parameters": {
"by": "id",
"value": "search-input",
"timeout": 5000
}
}
click_element
Clicks an element.
Parameters:
by(required): Locator strategyType: string
Enum: ["id", "css", "xpath", "name", "tag", "class"]
value(required): Value for the locator strategyType: string
timeout: Maximum time to wait for element in millisecondsType: 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 strategyType: string
Enum: ["id", "css", "xpath", "name", "tag", "class"]
value(required): Value for the locator strategyType: string
text(required): Text to enter into the elementType: string
timeout: Maximum time to wait for element in millisecondsType: 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 strategyType: string
Enum: ["id", "css", "xpath", "name", "tag", "class"]
value(required): Value for the locator strategyType: string
timeout: Maximum time to wait for element in millisecondsType: 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 strategyType: string
Enum: ["id", "css", "xpath", "name", "tag", "class"]
value(required): Value for the locator strategyType: string
timeout: Maximum time to wait for element in millisecondsType: 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 elementType: string
Enum: ["id", "css", "xpath", "name", "tag", "class"]
value(required): Value for the source locator strategyType: string
targetBy(required): Locator strategy for target elementType: string
Enum: ["id", "css", "xpath", "name", "tag", "class"]
targetValue(required): Value for the target locator strategyType: string
timeout: Maximum time to wait for elements in millisecondsType: 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 strategyType: string
Enum: ["id", "css", "xpath", "name", "tag", "class"]
value(required): Value for the locator strategyType: string
timeout: Maximum time to wait for element in millisecondsType: 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 strategyType: string
Enum: ["id", "css", "xpath", "name", "tag", "class"]
value(required): Value for the locator strategyType: string
timeout: Maximum time to wait for element in millisecondsType: 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 strategyType: string
Enum: ["id", "css", "xpath", "name", "tag", "class"]
value(required): Value for the locator strategyType: string
filePath(required): Absolute path to the file to uploadType: string
timeout: Maximum time to wait for element in millisecondsType: 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
local-only server
The server can only run on the client's local machine because it depends on local resources.
Enables browser automation using the Selenium WebDriver through MCP, supporting browser management, element location, and both basic and advanced user interactions.
- Features
- Supported Browsers
- Use with Goose
- Use with other MCP clients (e.g. Claude Desktop, etc)
- Development
- Tools
- License
Related Resources
Related MCP Servers
- -security-license-qualityA tool that enables automated browser control using Pyppeteer within the MCP framework, allowing navigation, screenshot capture, and element interaction with websites.Last updated -Apache 2.0
- Asecurity-licenseAqualityAn MCP service that automates Chrome browser control while bypassing anti-bot detection mechanisms, enabling web scraping, testing and automation on sites with sophisticated bot protection.Last updated -166MIT License
- -security-license-qualityA session-based MCP server that provides advanced browser automation capabilities, allowing users to control browsers, navigate websites, interact with elements, capture screenshots, generate PDFs, and manage cookies through natural language.Last updated -1MIT License