Playwright MCP Server
Headless browser primitives for AI agents when sites need real JS rendering.
Connect it
Settings → Connectors → Add custom connector
URL: https://nexgendata-mcp-proxy.steve-corbeil.workers.dev/playwright-mcp-server/mcpSettings → Apps & Connectors → Advanced → Developer mode
Create connector with URL: https://nexgendata-mcp-proxy.steve-corbeil.workers.dev/playwright-mcp-server/mcp{
"mcpServers": {
"playwright-mcp-server": {
"url": "https://nexgendata-mcp-proxy.steve-corbeil.workers.dev/playwright-mcp-server/mcp",
"headers": {
"Authorization": "<YOUR_AUTHORIZATION>"
}
}
}
}claude mcp add --transport http playwright-mcp-server https://nexgendata-mcp-proxy.steve-corbeil.workers.dev/playwright-mcp-server/mcp --header "Authorization: <value>"{
"servers": {
"playwright-mcp-server": {
"type": "http",
"url": "https://nexgendata-mcp-proxy.steve-corbeil.workers.dev/playwright-mcp-server/mcp",
"headers": {
"Authorization": "<YOUR_AUTHORIZATION>"
}
}
}
}17 tools, verified live
navigateNavigate the browser to a URL. Returns the final URL and page title.
screenshotread-onlyTake a PNG screenshot of the current page (or a specific element). Returns base64 PNG.
clickClick an element matched by CSS selector or visible text.
type_textType text into an input/textarea. Optionally clear first or press Enter after.
get_textread-onlyExtract visible text from the page or a specific element.
get_htmlread-onlyReturn the HTML of the page or a specific element.
evaluateEvaluate JavaScript in the page context. Use `return` for values or an expression.
select_optionChoose an option from a <select> element by value or visible label.
scrollScroll the page (or an element) in the given direction by `amount` pixels.
wait_forWait until a selector reaches a given state (visible|hidden|attached|detached).
get_linksread-onlyCollect all anchor hrefs, optionally filtered by regex.
extract_tableread-onlyExtract a standard HTML table as a list of row objects keyed by header.
page_pdfread-onlyRender the current page as PDF (headless only). Returns base64 PDF.
fill_formFill multiple form fields from a list of {selector, value} and optionally submit.
get_cookiesread-onlyReturn all cookies for the current browser context.
set_cookiesSet cookies for the current browser context.
close_browserClose the underlying browser, freeing resources.
Alternatives in Browser & Scraping
Compare →BRBrowserstackB
BrowserStack's Official MCP Server
SupadataB
Video transcripts, metadata and structured data from YouTube, TikTok, Instagram, X; web scraping.
Slack MCP ServerB
Catch up on Slack without reading it. Unreads, threads, search. Browser-session or hosted OAuth.
cloroB
Scrape AI answer engines and Google Search/News with country and state-level geo-targeting.
PDpdfrenderB
HTML and CSS to PDF MCP server with page headers, footers and page numbers. No headless browser.
PlayDropB
Publish, test and share browser games on PlayDrop from your AI agent.