Playwright MCP Server

A powerful Model Context Protocol (MCP) server that provides comprehensive browser automation capabilities using Playwright. This server enables AI assistants to interact with web pages, perform automated testing, web scraping, and complex browser-based workflows.

🚀 Quick Install for VSCode

Install this MCP server directly in VSCode with one click:

✨ Features

🌐 Complete Browser Control: Navigate, click, type, and interact with any web element
📸 Screenshot & Visual Testing: Capture full pages or specific elements
🔄 Tab Management: Open, close, and switch between multiple browser tabs
📝 Form Automation: Fill forms, select options, handle checkboxes and radio buttons
⏳ Smart Waiting: Wait for elements, network requests, or specific page states
🔍 Content Extraction: Get text, attributes, and data from web pages
💻 JavaScript Execution: Run custom JavaScript in the browser context
🛡️ Robust Error Handling: Comprehensive error handling with meaningful messages

📦 Installation

Prerequisites

Python 3.8 or higher
Node.js (required for Playwright browser installation)

Install from PyPI

pip install playwright-mcp-server
playwright install chromium

Install from Source

git clone https://github.com/nolecram/Build_MCP_Server.git
cd Build_MCP_Server
pip install -e .
playwright install chromium

🔧 Configuration

For MCP Clients

Add to your MCP client configuration:

{
  "mcpServers": {
    "playwright": {
      "command": "playwright-mcp-server",
      "args": []
    }
  }
}

For VSCode MCP Extension

Add to your VSCode settings:

{
  "mcp.servers": {
    "playwright": {
      "command": "playwright-mcp-server"
    }
  }
}

🛠️ Available Tools

Tool	Description	Parameters
`browser_navigate`	Navigate to a URL	`url`
`browser_click`	Click on an element	`selector`, `timeout?`
`browser_type`	Type text into an element	`selector`, `text`, `timeout?`
`browser_screenshot`	Take a screenshot	`path?`, `full_page?`
`browser_get_text`	Extract text from an element	`selector`, `timeout?`
`browser_wait_for_selector`	Wait for element to appear	`selector`, `timeout?`, `state?`
`browser_evaluate`	Execute JavaScript	`script`
`browser_new_tab`	Open a new tab	`url?`
`browser_close_tab`	Close current tab	-
`browser_get_title`	Get page title	-
`browser_get_url`	Get current URL	-

💡 Usage Examples

Web Scraping

# Navigate to a website
browser_navigate {"url": "https://example.com"}

# Wait for content to load
browser_wait_for_selector {"selector": ".content"}

# Extract information
browser_get_text {"selector": ".price"}

# Take a screenshot
browser_screenshot {"full_page": true}

Form Automation

# Fill out a form
browser_type {"selector": "#email", "text": "user@example.com"}
browser_type {"selector": "#password", "text": "secretpassword"}
browser_click {"selector": "#login-button"}

Testing Workflows

# Multi-step testing
browser_navigate {"url": "https://app.example.com"}
browser_click {"selector": "#feature-button"}
browser_wait_for_selector {"selector": ".success-message"}
browser_screenshot {"path": "test-result.png"}

🧪 Testing

Run the test suite:

# Install test dependencies
pip install pytest pytest-asyncio

# Run tests
pytest tests/

# Run with coverage
pytest --cov=playwright_mcp_server tests/

📚 Documentation

Comprehensive documentation is available in the docs directory:

🔒 Security

Runs in headless mode by default
Isolated browser contexts for each session
Automatic resource cleanup
Configurable timeout limits
No sensitive data logging

🤝 Contributing

We welcome contributions! Please see our contributing guidelines:

Fork the repository
Create a feature branch
Add tests for your changes
Ensure all tests pass
Submit a pull request

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

🙏 Acknowledgments

Built with Playwright for reliable browser automation
Implements the Model Context Protocol specification
Inspired by the need for robust browser automation in AI workflows

📈 Roadmap

Support for multiple browser engines (Firefox, Safari)
Advanced element selection strategies
Built-in visual regression testing
Performance monitoring and metrics
Browser extension interaction
Mobile browser simulation

⭐ Star this repository if you find it useful!

This server cannot be installed

security - not tested

license - permissive license

quality - not tested

How are these scores calculated?

A Model Context Protocol server that enables AI assistants to interact with web pages through browser automation, supporting web scraping, form filling, navigation, and other browser-based tasks using Playwright.

Related MCP Servers

mcp-playwright
executeautomation
A
security
A
license
A
quality
A Model Context Protocol server that provides browser automation capabilities using Playwright. This server enables LLMs to interact with web pages, take screenshots, and execute JavaScript in a real browser environment.
Last updated -
13
10,534
3,956
TypeScript
MIT License
Playwright MCP Server
showfive
-
security
F
license
-
quality
Provides a server utilizing Model Context Protocol to enable human-like browser automation with Playwright, allowing control over browser actions such as navigation, element interaction, and scrolling.
Last updated -
2
TypeScript
Puppeteer MCP Server
twolven
-
security
A
license
-
quality
A Model Context Protocol server that provides browser automation capabilities using Playwright, enabling LLMs to interact with web pages, take screenshots, and execute JavaScript in a real browser environment.
Last updated -
3
Python
Apache 2.0
Playwright MCP Server
BhanuTJ93
A
security
A
license
A
quality
A Model Context Protocol server that provides browser automation capabilities using Playwright, enabling LLMs to interact with web pages, take screenshots, generate test code, scrape web content, and execute JavaScript in real browser environments.
Last updated -
31
10,534
TypeScript
MIT License

View all related MCP servers

Playwright MCP Server