MCP cover image
See in Github
2025-04-12

Une implémentation MCP pour Selenium WebDriver

8

Github Watches

13

Github Forks

96

Github Stars

MCP Selenium Server

MCP-Selenium image

smithery badge

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

Video Demo (Click to Watch)

Watch the video

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:

  1. Clone the repository
  2. Install dependencies: npm install
  3. 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

  • https://suefel.com
  • Latest advice and best practices for custom GPT development.

  • Yusuf Emre Yeşilyurt
  • I find academic articles and books for research and literature reviews.

  • https://maiplestudio.com
  • Find Exhibitors, Speakers and more

  • Carlos Ferrin
  • Encuentra películas y series en plataformas de streaming.

  • Joshua Armstrong
  • Confidential guide on numerology and astrology, based of GG33 Public information

  • Emmet Halm
  • Converts Figma frames into front-end code for various mobile frameworks.

  • Elijah Ng Shi Yi
  • Advanced software engineer GPT that excels through nailing the basics.

  • lumpenspace
  • Take an adjectivised noun, and create images making it progressively more adjective!

  • https://appia.in
  • Siri Shortcut Finder – your go-to place for discovering amazing Siri Shortcuts with ease

  • apappascs
  • 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.

  • ShrimpingIt
  • Manipulation basée sur Micropython I2C de l'exposition GPIO de la série MCP, dérivée d'Adafruit_MCP230XX

  • jae-jae
  • MCP Server pour récupérer le contenu de la page Web à l'aide du navigateur sans tête du dramwright.

  • Mintplex-Labs
  • L'application tout-en-un desktop et Docker AI avec chiffon intégré, agents AI, constructeur d'agent sans code, compatibilité MCP, etc.

  • ravitemer
  • Un puissant plugin Neovim pour gérer les serveurs MCP (Protocole de contexte modèle)

  • patruff
  • Pont entre les serveurs Olllama et MCP, permettant aux LLM locaux d'utiliser des outils de protocole de contexte de modèle

  • pontusab
  • La communauté du curseur et de la planche à voile, recherchez des règles et des MCP

  • WangRongsheng
  • 🧑‍🚀 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.

  • n8n-io
  • 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.

  • av
  • Exécutez sans effort LLM Backends, API, Frontends et Services avec une seule commande.

    Reviews

    5 (1)
    Avatar
    user_nVkKFleW
    2025-04-17

    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!