LaunchKit · 2026
Back to Skills

playwright-mcp

Browser automation via Playwright MCP server.

88
23.0k downloads
by @spiceman161

Setup & Installation

openclaw skills install @spiceman161/playwright-mcp

Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:

npx clawhub install playwright-mcp

What This Skill Does

Runs a Playwright MCP server so your agent can control a real browser. It handles navigation, clicking, form filling, text extraction, and JavaScript execution across Chromium, Firefox, and WebKit.

When to use it

  • Scraping data from JavaScript-heavy pages that don't have an API
  • Filling out web forms and submitting them on behalf of the user
  • Checking if a deployed site loads and behaves correctly after changes
  • Pulling text or table data from behind-login pages
  • Taking screenshots of web pages for reports or monitoring

Example Workflow

Here's how your AI assistant might use this skill in practice.

INPUT

User asks: "Log into staging and check if the dashboard loads"

AGENT
  1. 1Starts the Playwright MCP server with Chromium
  2. 2Navigates to the login page
  3. 3Types credentials into the username and password fields
  4. 4Clicks the submit button
  5. 5Takes a snapshot of the dashboard to verify it loaded
OUTPUT

Dashboard loaded with all widgets visible, no errors on page