
MCP-Selenium
Une implémentation MCP pour Selenium WebDriver
8
Github Watches
13
Github Forks
96
Github Stars
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
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
相关推荐
I find academic articles and books for research and literature reviews.
Confidential guide on numerology and astrology, based of GG33 Public information
Emulating Dr. Jordan B. Peterson's style in providing life advice and insights.
Your go-to expert in the Rust ecosystem, specializing in precise code interpretation, up-to-date crate version checking, and in-depth source code analysis. I offer accurate, context-aware insights for all your Rust programming questions.
Advanced software engineer GPT that excels through nailing the basics.
Take an adjectivised noun, and create images making it progressively more adjective!
Découvrez la collection la plus complète et la plus à jour de serveurs MCP sur le marché. Ce référentiel sert de centre centralisé, offrant un vaste catalogue de serveurs MCP open-source et propriétaires, avec des fonctionnalités, des liens de documentation et des contributeurs.
L'application tout-en-un desktop et Docker AI avec chiffon intégré, agents AI, constructeur d'agent sans code, compatibilité MCP, etc.
Manipulation basée sur Micropython I2C de l'exposition GPIO de la série MCP, dérivée d'Adafruit_MCP230XX
Plateforme d'automatisation de workflow à code équitable avec des capacités d'IA natives. Combinez le bâtiment visuel avec du code personnalisé, de l'auto-hôte ou du cloud, 400+ intégrations.
🧑🚀 全世界最好的 LLM 资料总结 (数据处理、模型训练、模型部署、 O1 模型、 MCP 、小语言模型、视觉语言模型) | Résumé des meilleures ressources LLM du monde.
Un puissant plugin Neovim pour gérer les serveurs MCP (Protocole de contexte modèle)
Une liste organisée des serveurs de protocole de contexte de modèle (MCP)
MCP Server pour récupérer le contenu de la page Web à l'aide du navigateur sans tête du dramwright.
Reviews

user_nVkKFleW
As a dedicated user of mcp-selenium, I am thoroughly impressed with its capabilities and performance. This tool, created by the brilliant Angie Jones, seamlessly integrates with Selenium to enhance test automation. The clear documentation and ease of use make it an invaluable asset for any QA engineer. Highly recommended!