Setup & Installation
openclaw skills install @ramspan/pascal-playwright-mcp
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
npx clawhub install pascal-playwright-mcp
What This Skill Does
Playwright MCP exposes browser automation as MCP tools, letting agents control Chrome, Firefox, or WebKit. Navigate pages, interact with forms, run JavaScript, and extract data from any website.
Wrapping Playwright in MCP exposes full browser control to any agent without custom scripting or manual browser driver configuration.
When to use it
- Automating login flows on web applications
- Scraping structured data from dynamic web pages
- Filling and submitting forms programmatically
- Taking screenshots of pages for visual checks
- Testing multi-step browser workflows across browsers
Example Workflow
Here's how your AI assistant might use this skill in practice.
INPUT
User asks: Extract all rows from the pricing table at example.com/pricing
AGENT
- 1Navigate to the page using browser_navigate
- 2Inspect structure with browser_snapshot
- 3Run browser_evaluate with a script querying all table rows
- 4Parse the returned array into structured data
OUTPUT
Array of pricing tier objects with names and values extracted from the table