Is the Browserless MCP server free?

Yes. Activepieces is open source and free to start, and the MCP server is included on every plan, from the free cloud tier to any self-hosted deployment.

How do I connect Browserless to Claude or Cursor?

Connect Browserless in Activepieces, enable the server under Settings → MCP Server, then paste your server URL into your client config. It authenticates over OAuth on first use.

What can my agent do in Browserless?

It can call 16 tools, including Capture Screenshot, Generate PDF, Scrape URL, and chain them with steps in other apps inside the same run.

Is it safe to let an agent call Browserless?

Connections use OAuth2 with limited scopes and are stored under 256-bit encryption, with no API to read them back, so an agent gets scoped access rather than your keys.

Browserless MCP server

Browserless is a headless browser automation tool that allows you to scrape websites, take screenshots, and more.

Browserless is not a separate install. One Activepieces MCP server exposes it alongside 770+ other apps, behind a single URL.

Start building See the Browserless integration

Tools: 16
Works with: Any MCP client
Auth: Custom auth
License: MIT, open source
Updated: October 2026

About the Browserless MCP server

Connect Browserless once in Activepieces and every action it ships becomes a tool your assistant can call, behind the same server URL as the rest of your apps. Your agent reaches Browserless and 770+ other apps over a single connection, on our cloud or a self-hosted install.

Tools

Browserless tools your AI can run

Once connected, your assistant can call any of these Browserless actions by asking in plain language.

Capture Screenshot
Take a screenshot of a web page
13 fields
Generate PDF
Convert a web page to PDF
31 fields
Scrape URL
Extract content from a web page
20 fields
Run BQL Query
Execute Browser Query Language (BQL) GraphQL-based queries for advanced browser automation
19 fields
Get Website Performance
Analyze website performance metrics using Lighthouse
14 fields
Get Page Content
Load a page in a real browser and return its fully rendered HTML, including content added by JavaScript.
10 fields
Smart Scrape
Get a page as markdown, text, HTML or links. Browserless tries a fast fetch first and falls back to a real browser, proxy or CAPTCHA solving when the site blocks it.
9 fields
Search the Web
Search the web (pages, news or images) and optionally read each result page as markdown.
13 fields
Map Website URLs
List the URLs of a website from its sitemap and links, optionally ordered by relevance to a search term.
8 fields
Start Crawl
Start crawling a website in the background. Browserless follows links and scrapes every page it finds; use Get Crawl Results to read them.
11 fields
Get Crawl Results
Get the status of a crawl and one page of its scraped pages.
2 fields
List Crawls
List your recent crawls with their status and progress.
3 fields
Cancel Crawl
Stop a running crawl. Pages already scraped stay available.
1 field
Unblock Page
Open a page that blocks bots (Cloudflare, CAPTCHAs and similar) and return its HTML, cookies and a screenshot.
14 fields
Run Puppeteer Function
Run your own Puppeteer code in a Browserless browser and return what it returns.
4 fields
Custom API Call
Make a custom API call to a specific endpoint
10 fields

Give your assistant Browserless

Connect Browserless once and every tool above is callable from Claude, Cursor or any MCP client, behind the same server URL as 770+ other apps. Free to start.

Get your server URL Talk to sales

Browserless MCP, answered.

No. That is the point of it. One Activepieces server exposes Browserless alongside every other piece you connect, so your client keeps a single connection.