Playwright MCP
Let agents verify UI changes in a real browser.
Playwright MCP gives agents the ability to control a headless browser. This is useful when you want agents to verify that UI changes actually work instead of only checking the code.
What agents can do
With Playwright MCP enabled, agents can:
- Navigate to your app's live preview
- Click links and buttons
- Fill out forms
- Take screenshots of the UI and send them back in chat
- Check the JavaScript console for errors
Screenshots taken by agents appear as Artifacts in the chat. This makes it easy to review visual changes without running the app yourself.
Setup
- Go to Project Settings -> Skills and MCPs.
- Enable Playwright.
Playwright does not require an API key.
When to use it
Ask agents to use Playwright when a change affects user-facing UI, browser behavior, or JavaScript. For example:
Use Playwright to verify the modal opens, submit the form, and send me a screenshot.After the layout change, check the page at desktop and mobile widths and look for console errors.