Integration · Developer tools

Connect Claude & ChatGPT to Browserless

Give your AI a real browser in the cloud. With Browserless it can open a web page, wait for JavaScript to run and read the result as markdown or HTML, pull out elements by CSS selector, take screenshots and save pages as PDFs. It can also map a site's links, run a web search and run a Lighthouse performance audit.

Connect Browserless free

Free plan, no credit card. Takes about a minute.

Try asking

“Take a full-page screenshot of our pricing page.”
The AI loads the page in a headless browser and returns a screenshot of the whole page.
“Save this article as a PDF with A4 paper and no margins.”
It renders the page to a PDF using the paper format and margins you asked for.
“Get the prices and product names from this shop page.”
It loads the page and uses CSS selectors to extract the matching elements with their text and attributes.

What your AI can do

Screenshots and PDFs

Take screenshots of a full page, one element or a set viewport, and render pages or raw HTML to PDF with your own paper format and margins.

Scraping rendered pages

Read pages after JavaScript has run, as markdown or HTML, or extract exact elements with CSS selectors.

Search, site maps and audits

Run web searches with country, language and time filters, discover a site's URLs, and run Lighthouse performance audits.

“Read this page and summarize it for me.”
It loads the page in a cloud browser, returns the content as markdown and the AI summarizes it.
“List all the blog URLs on example.com.”
It maps the site's links from its sitemap and pages, ranked by relevance to 'blog'.
“How fast is our homepage?”
It runs a Lighthouse performance audit on the page and reports the scores and metrics.

9 tools for Browserless

These tools are switched on when you connect. You can switch any of them off, or require your approval before it runs.

create_pdfChanges dataRender a web page by `url` (or raw `html`) to a PDF document. Use `options` for paper format, margins and background printing.
get_page_htmlChanges dataOpen a page in a headless browser and return the fully rendered HTML after JavaScript runs. Pass `url` (or raw `html`).
list_profilesList saved browser profiles (stored logins and cookies) that can be passed as `profile` to other tools.
map_site_linksChanges dataDiscover the URLs of a website starting from `url`, using its sitemap and links. Optional `search` to rank links by relevance and `limit` (max 5000).
run_performance_auditChanges dataRun a Lighthouse performance audit on the page at `url` and return scores and metrics.
scrape_elementsChanges dataExtract specific elements from a rendered page using CSS selectors in `elements`, returning their text, attributes and positions. Pass `url` too.
scrape_pageChanges dataLoad a web page in a cloud browser and return its content, e.g. as markdown or HTML, via `formats`. Requires `url`; optional `wait_for`, `actions` and include/exclude tags.
search_webChanges dataRun a web search for `query` and return results, optionally scraping each result. Filters include `country`, `lang`, `limit`, `sources` (web, news, images) and `tbs` time range.
take_screenshotChanges dataTake a screenshot of a web page by `url` (or raw `html`). Optional `selector` for one element, `viewport` for size and `options` such as full page or image type.

Set up in three steps

1
Pick the app
Create a free PipMCP account and choose Browserless from the app list.
2
Paste your key
Paste your Browserless API token. Log in at browserless.io/account and copy the token shown under API Key on the account home page. To use a separate token, click Manage API keys and Create API key. A new token is shown only once.
3
Add the link to your AI
You get a personal MCP link. Add it to Claude, ChatGPT or Cursor:
1. Click your name, then Settings › Connectors › Add custom connector.
2. Paste your link as the Remote MCP server URL.
3. Switch it on from the + menu in a chat.

Questions

What can the AI do in Browserless?

The AI can load web pages in a cloud browser and return the rendered HTML or content as markdown, extract elements with CSS selectors, take screenshots and create PDFs. It can also map a site's URLs, run web searches, run Lighthouse performance audits and list your saved browser profiles.

Does the AI see my Browserless API token?

No. Your Browserless API token is encrypted at rest and never shown to the AI. After you save it, it is not shown again, not even to you. The AI only sees the results of the tools it calls.

Can I control what the AI is allowed to do?

Yes. You choose which tools are switched on, for example only screenshots and PDFs. Any tool can require your approval before it runs, and every tool call is logged.

Does it work with ChatGPT?

Yes. In ChatGPT go to Settings › Apps & Connectors › Advanced and turn on Developer mode, then add your PipMCP link. Developer mode needs a paid ChatGPT plan: Plus, Pro, Business or Enterprise. The same link also works in Claude (Settings › Connectors › Add custom connector), Cursor and other MCP clients.

What does it cost?

PipMCP has a free plan with no credit card required. Paid plans bill per completed task. You also need your own Browserless account.

Does the browser run on my computer?

No. Each page is loaded in a headless browser in the Browserless cloud. The AI gets back the result, such as the page content, a screenshot or a PDF. Saved browser profiles with stored logins and cookies can be passed to the tools when a page needs them.