playwright-mcp-server
Headless browser primitives for AI agents when sites need real JS rendering.
Community: Submitted by a user or imported; check the owner before granting accessOnlineAPI key requiredGlobalFreeRead-only
What it can do
What data it sees
Do you need an account
An API key from the service settings is required
Headless browser primitives for AI agents when sites need real JS rendering.
Server tool list (17)
Raw names from tools/list. Only developers need these.
| navigate | Navigate the browser to a URL. Returns the final URL and page title. |
| screenshot | Take a PNG screenshot of the current page (or a specific element). Returns base64 PNG. |
| click | Click an element matched by CSS selector or visible text. |
| type_text | Type text into an input/textarea. Optionally clear first or press Enter after. |
| get_text | Extract visible text from the page or a specific element. |
| get_html | Return the HTML of the page or a specific element. |
| evaluate | Evaluate JavaScript in the page context. Use `return` for values or an expression. |
| select_option | Choose an option from a <select> element by value or visible label. |
| scroll | Scroll the page (or an element) in the given direction by `amount` pixels. |
| wait_for | Wait until a selector reaches a given state (visible|hidden|attached|detached). |
| get_links | Collect all anchor hrefs, optionally filtered by regex. |
| extract_table | Extract a standard HTML table as a list of row objects keyed by header. |
| page_pdf | Render the current page as PDF (headless only). Returns base64 PDF. |
| fill_form | Fill multiple form fields from a list of {selector, value} and optionally submit. |
| get_cookies | Return all cookies for the current browser context. |
| set_cookies | Set cookies for the current browser context. |
| close_browser | Close the underlying browser, freeing resources. |