Browserless MCP: a hosted headless browser for your AI app

How to set up Browserless for Claude, ChatGPT or Cursor

1. 1Click Connect Browserless free and sign in with your Browserless account.
2. 2Every tool starts on. Screenshots, PDFs and HTML fetches are simple reads; running custom Puppeteer code or getting past bot protection is a bigger step, so switch those tools off unless someone needs them.
3. 3Add ContextGate to your AI app as a connector or MCP server. The steps for each app are on the Works with page.
4. 4Ask your AI app to take a full-page screenshot of your pricing page and save it as a PDF too, then look in Activity for both calls.

Browser jobs to hand to Claude or Cursor

• Fetch the full HTML of a page, including content rendered by JavaScript.
• Scrape specific elements from a page by CSS selector.
• Take a PNG or JPEG screenshot, full page if you like, or generate a PDF of a URL.
• Run a Puppeteer script and download the files Chrome saved while it ran.

Limits for an AI-driven browser

• Switch off custom Puppeteer execution and the bot-protection tool, and keep screenshots, PDFs and scraping.
• Set a policy to warn on, or block, calls that run custom code.
• Activity lists every URL your AI apps asked Browserless to visit.

What you get with Browserless and ContextGate

• Your AI apps can use BrowserlessClaude, Cursor, ChatGPT and other AI apps reach Browserless through the one ContextGate connection you add to them.
• You choose which tools they can useSwitch off any Browserless tool you don't want used. It's hidden from your AI apps and refused if called.
• Every call is checked and recordedYour policies check each call (for example, personal data is hidden and secrets are blocked), and Activity keeps a record of it.

ContextGate sees only the tool calls that go through it, not your AI app's built-in tools or your chats.

Browserless tools

Examples of what your AI apps can do in Browserless. You'll see the exact list of tools after you connect it.

• Download file using Puppeteer scriptThis tool allows downloading files that chrome has downloaded during the execution of puppeteer code. it sets up a blank page, creates a fresh download directory, injects the provided code, and execut
• Execute Custom FunctionA tool that allows executing custom puppeteer scripts via http requests. this endpoint enables users to run browser automation tasks without managing their own infrastructure.
• Fetch HTML ContentThis tool fetches the complete html content of a webpage using browserless's content api. it's designed to retrieve the full html contents of any website, including dynamically generated content.
• Generate PDF from webpageThis tool generates a pdf from a specified webpage using browserless's pdf generation api. it allows specifying the url of the webpage along with parameters such as format, filename, and waituntil opt
• Scrape webpage content using CSS selectorsA tool to extract structured content from a webpage by specifying css selectors. the tool navigates to the specified url, waits for the page to load (including parsing and executing javascript), and r
• Take ScreenshotA tool that captures a screenshot of a webpage using browserless's screenshot api. the tool takes a url and returns either a png or jpeg image. it includes options for full page capture, image type, q
• Unblock Protected ContentThis tool provides access to content from websites that implement bot protection mechanisms. it is designed to bypass various types of protection (such as captcha and bot detections) and return the ht