playwright-mcp

Automate browser interactions and web scraping with the Playwright MCP server.

3|1|Updated Feb 2, 2026
One-click install
npx skills add https://github.com/HouseGarofalo/claude-code-base --skill playwright-mcp-housegarofalo
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: playwright-mcp
Source: https://github.com/HouseGarofalo/claude-code-base/tree/main/.claude/skills/playwright-mcp
Command: npx skills add https://github.com/HouseGarofalo/claude-code-base --skill playwright-mcp-housegarofalo

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill automates browser interactions, web scraping, and end-to-end testing, eliminating the need for manual navigation and data collection in web applications.

Core Features & Use Cases

  • Browser Navigation: Navigate to URLs, go back, manage tabs, and close pages.
  • User Interaction: Click elements, type into forms, select options, hover, drag, and upload files.
  • Data Scraping & Screenshots: Extract page content, capture screenshots, and retrieve console logs or network requests.
  • Use Case: Automate the process of filling out a complex online form across multiple pages, ensuring all fields are correctly populated and submitting the form upon completion.

Quick Start

Use the playwright-mcp skill to navigate to 'https://example.com' and take a full-page screenshot.

Frequently Asked Questions about playwright-mcp

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate web scraping and extract page content without manual navigation?

Browser automation for web scraping is handled by using the Playwright MCP server to navigate URLs, extract page content, and retrieve console logs or network requests automatically. It eliminates manual navigation by supporting headless browser execution across Chrome, Firefox, and WebKit.

Can I use Playwright MCP for e2e testing across different web browsers?

Yes, Playwright MCP supports end-to-end testing by automating browser interactions like clicking elements and filling forms across Chrome, Firefox, and WebKit. You can execute tests in either headless or headed browser modes to validate web application behavior.

What is the best way to capture full-page screenshots and generate PDFs from web pages?

Capturing full-page screenshots and generating PDFs is achieved by automating browser navigation with the Playwright MCP server. Once the page loads, the Skill extracts page content and triggers screenshot capture or PDF generation directly from the automated browser session.

Does browser automation via Playwright support complex user interactions like form filling and file uploads?

Playwright browser automation supports complex user interactions including clicking elements, typing into forms, selecting options, hovering, dragging, and uploading files. This enables the automation of multi-page online form submissions with correctly populated fields.

How do I navigate multiple tabs and manage browser pages during web scraping tasks?

Browser navigation during web scraping tasks is managed by the Playwright MCP server, which supports going back, managing tabs, navigating to URLs, and closing pages. This allows comprehensive automation of complex multi-page workflows.