playwright

Automate browser interactions and screenshots via Playwright MCP on a VNC display.

14|4|Updated Nov 22, 2025
One-click install
npx skills add https://github.com/pacphi/sindri --skill playwright-pacphi
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: playwright
Source: https://github.com/pacphi/sindri/tree/main/docker/lib/extensions/vf-playwright-mcp/resources
Command: npx skills add https://github.com/pacphi/sindri --skill playwright-pacphi

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill enables Claude to automate browsers through MCP, with a display session via VNC.

Core Features & Use Cases

  • Navigation & Interaction: Open pages, click elements, fill forms.
  • Screenshots & Tests: Capture screenshots and run visual verifications.
  • DOM & Performance: Query DOM, inspect performance data.

Quick Start

Navigate to a page and take a full-page screenshot.

Frequently Asked Questions about playwright

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

FAQPage Schema
How do I automate browser interactions and take screenshots with Playwright?

Browser automation with Playwright lets you programmatically navigate pages, click elements, fill forms, and capture screenshots. This Skill exposes Playwright MCP commands—navigate, click, type, screenshot, evaluate—to control a Chromium browser instance and access visual output via VNC display for testing and scraping workflows.

Can I use Playwright for web scraping and visual testing on a graphical display?

Yes. Playwright MCP automates web scraping by querying DOM, extracting content, and executing JavaScript, while VNC display access enables visual verification and screenshot capture. The Skill combines browser control with graphical output for end-to-end testing and data extraction.

What browser automation tasks can I perform with the MCP server?

The Playwright MCP server supports navigating to URLs, clicking and typing into form controls, waiting for dynamic content to load, executing JavaScript, querying page content, generating full-page screenshots, managing browser context, and health checks. All commands communicate via stdio-based MCP protocol.

Do I need a display or VNC setup to run browser automation with this Skill?

Yes. This Skill requires VNC access on Display :1 to expose the browser graphical interface. The Chromium instance launches on a specific display, enabling screenshot capture and visual testing workflows that depend on rendered output.

How do I integrate Playwright MCP with my automation workflow?

The Skill integrates via MCP SDK for stdio-based communication, exposing a set of browser commands. Pass parameters to navigate, interact, and inspect pages; the server manages the Chromium browser context and returns results—content, URLs, screenshots—for downstream processing.

What are the limitations when automating browsers for performance or complex interactions?

Playwright MCP depends on active VNC display and Chromium availability. Heavy JavaScript execution, complex waits, and large-scale scraping may require tuning timeouts and selector strategies. Performance inspection is supported but complex interactions must be sequenced through individual commands.