playwright-mcp

Playwright is Microsoft's browser automation library, the one half the web's end-to-end tests run on. This MCP server hands it to the agent: the model opens a page, clicks, fills a form, waits for the load and reads the result. That lets the agent check on its own that a landing-page form submits, walk the sign-up flow after a change, or pull data from a site that shows nothing without JavaScript.

The main difference from "download the HTML and parse it" is that the agent works against the page's accessibility tree, the same structure a screen reader reads, not against the source. It sees a button as a button and a field as a field, and it does not have to guess selectors from class names that change on the next deploy. It suits anyone who wants the agent to check the live site, not just the code.