Playwright MCP Explorer
An intelligent tool that uses MCP to autonomously explore websites and generate Playwright tests from natural language descriptions.
WIP # - Currently under construction
Playwright_MCP_Explorer
Intelligent Playwright test generation tool using MCP that both autonomously explores websites and generates tests, as well as generates specific scenarios based on the user's verify statements.
MCP-Playwright is a revolutionary automated testing framework that combines the power of Model Context Protocol (MCP) with Playwright to generate comprehensive test suites using natural language descriptions and autonomous website exploration.
Key Features
-AI-Powered Test Generation: Convert natural language statements into robust Playwright tests
-Autonomous Website Exploration-Automatically discover and test website functionality Natural Language Scenarios
-Write tests using simple verify statements
-Smart Selector Generation-Automatically generates resilient, maintainable selectors
-Cross-Browser Testing-Run tests across Chromium, Firefox, and WebKit
1. Natural Language Test Generation Write simple verify statements and let AI generate comprehensive tests:
2. Autonomous Website Exploration Let the system explore websites and generate tests automatically:
Prerequisites Node.js 18+ npm or yarn Git
Installation
1. Clone the repository
git clone https://github.com/yourusername/mcp-playwright-suite.git
,cd mcp-playwright-suite
2. Install dependencies
npm install
3. Install Playwright browsers
npx playwright install --with-deps
4. Build the project
npm run build
Usage Examples
Natural Language Test Generation
1. Edit scenarios in test-data/scenarios.json:
"scenarios": [
{
"id": "login-flow",
"name": "User Login Flow",
"url": "https://myapp.com/login",
"verifyStatements": [
"Verify email field exists",
"Verify password field exists",
"Verify login button is present",
"Verify form validation shows error for invalid email"
]
}
]
}
2. Generate tests:
npm run mcp:generate scenarios
3. Run tests:
npm test tests/generated/login-flow.spec.ts
4. Website Exploration
npm run mcp:generate explore https://github.com "GitHub Homepage Test"
5. Interactive mode for multiple operations
npm run mcp:generate interactive
AI-Powered Features
Smart Natural Language Processing
The system understands various types of verify statements:
Presence checks: "is present", "exists", "is visible"
Text content: "contains", "displays", "shows"
State checks: "disabled", "enabled", "checked"
Validation: "shows error", "validation"
Intelligent Selector Generation Automatically maps natural language to robust selectors:
"header" → header, h1, h2, h3, h4, h5, h6
"navigation menu" → nav, .nav, .navigation, .menu
"submit button" → button[type="submit"], input[type="submit"]
"email field" → input[type="email"], input[name*="email"]
Test Quality Features
-Resilient Selectors - Prioritizes data-testid, aria-label, and semantic selectors
-Wait Conditions - Automatic handling of dynamic content loading
-Error Handling - Screenshot capture on test failures
-Cross-Browser - Tests run on Chromium, Firefox, and WebKit
-Parallel Execution - Fast test execution with worker processes
MCP Server Configuration ( mcp-config.json)
{
"mcpServers": {
"filesystem": {
"command": "npx",
"args": ["-y", "@modelcontextprotocol/server-filesystem", "./tests", "./test-data"]
}
},
"testGeneration": {
"outputDir": "./tests/generated",
"defaultTimeout": 30000,
"browsers": ["chromium", "firefox", "webkit"]
}
}
Playwright Configuration Fully configurable through playwright.config.ts with sensible defaults for:
-Multi-browser testing
-Parallel execution
-HTML reporting
-Screenshot and video capture
Available Commands
Test Generation
npm run mcp:generate scenarios # Generate from scenarios file
npm run mcp:generate explore <url> <name> # Explore website and generate
npm run mcp:generate interactive # Interactive mode
Test Execution
npm test # Run all tests
npm run test:headed # Run with visible browser
npm run test:debug # Debug mode
npm run test:ui # Playwright UI mode
Example Generated Test From the verify statement "Verify header is present and contains 'Welcome'":
test.describe('Homepage Verification', () => {
test.beforeEach(async ({ page }) => {
await page.goto('https://example.com');
await page.waitForLoadState('networkidle');
});
test('Verify header is present and contains \'Welcome\'', async ({ page }) => {
// Navigate to the target URL
Contributing
I welcome contributions! Please see our Contributing Guide for details.
- Fork the repository
- Create a feature branch (git checkout -b feature/amazing-feature)
- Commit your changes (git commit -m 'Add amazing feature')
- Push to the branch (git push origin feature/amazing-feature)
- Open a Pull Request
Acknowledgments
-Playwright - For the excellent browser automation framework
-Model Context Protocol - For enabling AI-powered automation
-TypeScript - For type safety and developer experience
相关服务器
Scout Monitoring MCP
赞助Put performance and error data directly in the hands of your AI assistant.
Alpha Vantage MCP Server
赞助Access financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
MCP Reasoner
A reasoning engine with multiple strategies, including Beam Search and Monte Carlo Tree Search.
Layered Code
An AI-assisted web development tool for creating, modifying, and deploying code through natural language conversations.
DINO-X
Advanced computer vision and object detection MCP server powered by Dino-X, enabling AI agents to analyze images, detect objects, identify keypoints, and perform visual understanding tasks.
Agent Evals by Galileo
Bring agent evaluations, observability, and synthetic test set generation directly into your IDE for free with Galileo's new MCP server
FLUX Image Generator
Generate images using Black Forest Lab's FLUX model.
Remote MCP Server (Authless)
An authentication-free, remote MCP server deployable on Cloudflare Workers. Customize tools directly in the source code and deploy via Cloudflare or locally.
MCP Server
A cross-platform MCP server implementation for Amazon Q and Claude, providing multiple tools in a single executable.
Jira Context MCP
MCP server to provide Jira Tickets information to AI coding agents like Cursor.
oclif MCP Server Plugin
An oclif CLI plugin that automatically discovers and serves commands via the Model Context Protocol (MCP).
DevStandards
Provides AI agents with access to development best practices, security guidelines, and coding standards.