Integration

Browserless integration

Headless browser automation and web scraping API. Run Puppeteer, Playwright, or raw Chrome in the cloud. Features include PDF generation, screenshots, web scraping, automated testing, and JavaScript rendering. Scales to thousands of concurrent sessions with built-in proxy rotation and captcha handling.

Connect Browserless How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Browserless.Built from the 13 Browserless tools below, on the connection you add once.

Common Browserless use cases

SEO auditing
complex scraping
price monitoring
data collection
competitive intelligence
SEO pre-rendering
invoice generation
archiving web pages
research automation
thumbnail generation

What you can do with Browserless

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Content, 3 operations

get_page_contentGet page contentPOSTGets the fully rendered HTML of a page after JavaScript execution. Returns complete DOM content. Use for indexing SPAs or processing dynamic content.
scrape_contentScrape contentPOSTScrapes content from rendered webpages. Specify CSS selectors to extract data. Waits for JavaScript rendering before extraction. Returns structured element data.
unblock_urlUnblock urlPOSTAccesses protected URLs using anti-detection techniques. Residential proxies, browser fingerprinting, and cookie handling. Returns page content or browser session.

Page, 2 operations

export_pageExport pagePOSTFetches a URL and returns its content in the native format (HTML, PDF, image, ZIP). Use when content type is unknown or when bundling a page with all its resources.
smart_scrapeSmart scrapePOSTScrapes a URL using AI-powered fallbacks that handle bot-protection, JavaScript rendering, and CAPTCHAs. Returns HTML, Markdown, PDF, screenshot, or links.

Browser, 1 operation

connect_websocketConnect websocketGETReturns WebSocket URL for direct browser connection. Connect Puppeteer or Playwright to remote Chrome. Full DevTools Protocol access.

File, 1 operation

download_fileDownload filePOSTDownloads files by running Puppeteer code in a browser. Navigate to a page, trigger a download, and receive the file binary. Supports any file type Chrome can download.

Function, 1 operation

run_functionRun functionPOSTExecutes custom JavaScript in a browser context. Write Puppeteer-style code for complex automation. Full access to page manipulation and data extraction.

Pdf, 1 operation

generate_pdfGenerate pdfPOSTGenerates a PDF from a webpage URL or raw HTML. Configure page size, margins, headers/footers, and rendering options. Returns PDF binary data.

Performance, 1 operation

performance_auditPerformance auditPOSTRuns Lighthouse audit on a URL. Returns performance score, metrics (LCP, FID, CLS), accessibility score, SEO score, and improvement suggestions.

Screenshot, 1 operation

take_screenshotTake screenshotPOSTTakes a screenshot of a webpage. Configure viewport size, image format (PNG/JPEG), quality, and capture region. Supports full page or visible area.

Search, 1 operation

search_webSearch webPOSTSearches the web (or news/images) and returns ranked results. Supports language and country filtering, time range, and optional page scraping.

Site, 1 operation

map_siteMap sitePOSTDiscovers all URLs on a website or sitemap. Returns page URLs with titles and descriptions. Supports sitemap-guided discovery and subdomain crawling.

Use Browserless from Claude Code, Cursor or Codex

Connect Browserless in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Browserless operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Browserless

Create your workspace
Sign up free. Nothing to install.
Connect Browserless once
Add your Browserless connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.

Browserless integration FAQ

What can you do with the Browserless integration?

LiveContext exposes 13 operations on Browserless, covering content, page, browser and file. Common uses include SEO auditing, complex scraping and price monitoring.