RunAutomation MCP Server

A comprehensive Model Context Protocol (MCP) server for Playwright automation, providing 100+ tools for web testing, browser automation, and quality assurance tasks.

Table of Contents

• Why Use This MCP Server?
• Installation
• Configuration
• Available Tools
• Features
• Usage Examples
• Author
• Contributing
• Issues and Support
• License
• Acknowledgments

Why Use This MCP Server?

Model Context Protocol (MCP)

The Model Context Protocol is an open standard that enables seamless integration between AI assistants and external tools. This MCP server allows AI models (like Claude, GPT, etc.) to:

• Execute browser automation directly through natural language commands
• Perform quality assurance tasks without manual scripting
• Generate test code by observing user interactions
• Run comprehensive test suites with visual regression, accessibility, and cross-browser testing
• Integrate testing into AI workflows for autonomous test creation and execution

Key Benefits

• AI-Driven Testing: Let AI assistants write and execute tests based on requirements
• Natural Language Control: Control Playwright through conversational commands
• Comprehensive Coverage: 100+ tools covering every aspect of web testing
• Production-Ready: Built on Playwright's reliable automation framework
• Extensible: Easy to integrate into existing testing workflows
• Open Source: MIT licensed for commercial and personal use

Use Cases

• Automated Testing: Create and run browser automation tests
• Visual QA: Perform visual regression testing and cross-browser validation
• Accessibility Audits: Run WCAG compliance checks
• PDF Testing: Validate PDF generation and content
• API Testing: Test backend APIs alongside UI tests
• Test Generation: Record user actions and generate test code
• CI/CD Integration: Run tests in continuous integration pipelines

Installation

Prerequisites

• Node.js 18 or higher
• npm or yarn package manager

### Local Development Installation

1. Clone the repository:
```bash
git clone https://github.com/tayyabakmal1/runautomation-mcpserver.git
cd runautomation-mcpserver

2. Install dependencies:

npm install

3. Build the project:

npm run build

4. Run tests (optional):

npm test

Configuration

Claude Desktop Integration

To use this MCP server with Claude Desktop, add the following configuration to your Claude Desktop config file:

Windows: %APPDATA%\Claude\claude_desktop_config.json macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Linux: ~/.config/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "playwright": {
      "command": "npx",
      "args": [
        "--directory",
        "/your-playwright-mcp-server-clone-directory",
        "run",
        "runautomation-mcpserver"
      ]
    }
  }
}

Environment Variables

You can configure the server using environment variables:

# Browser configuration
PLAYWRIGHT_BROWSER=chromium  # chromium, firefox, webkit
PLAYWRIGHT_HEADLESS=true     # true or false

# Video recording
PLAYWRIGHT_VIDEO_DIR=./videos
PLAYWRIGHT_VIDEO_QUALITY=100

# Session management
MAX_SESSIONS=10
SESSION_TIMEOUT=3600000      # milliseconds

Available Tools

Browser Automation (50+ tools)

• playwright_navigate - Navigate to URL
• playwright_click - Click element
• playwright_fill - Fill input field
• playwright_select - Select dropdown option
• playwright_hover - Hover over element
• playwright_screenshot - Take screenshot
• playwright_evaluate - Execute JavaScript
• playwright_upload_file - Upload file
• playwright_download_file - Download file
• `pla

... View full README on GitHub