Skip to main content

Browserless MCP Server

The Browserless MCP server gives AI assistants full browser automation capabilities through the Model Context Protocol. Connect Claude Desktop, Cursor, VS Code, Windsurf, or any MCP-compatible client to the hosted server and start scraping, searching, mapping, crawling, running Lighthouse audits, exporting, downloading, and running custom browser code — no infrastructure required.

Prerequisites

  • A Browserless account - either an API token from your account dashboard, or OAuth sign-in
  • An MCP-compatible client (Claude Desktop, Cursor, VS Code, Windsurf, etc.)

Hosted Server

Browserless provides a hosted MCP server ready to use:

https://mcp.browserless.io/mcp

No installation or environment variables required. See Authentication for how to connect.

Authentication

The hosted server supports three authentication methods:

MethodBest for
OAuth (Browserless account login)Clients that support OAuth — no token needed
Authorization headerClients that support custom headers
token query parameterURL-only clients (e.g. Claude.ai custom connectors)

When multiple methods are present, they are evaluated in this order: Authorization header (plain API key) → token query parameter → OAuth JWT.

OAuth

For clients that support OAuth (for example Claude Desktop or Cursor), the hosted server can authenticate you through your Browserless account - no API token required. When you connect, your client will open a browser window to sign in. After authenticating, the server resolves your account automatically.

OAuth is enabled on the hosted server at https://mcp.browserless.io/mcp with no extra configuration needed.

API Token

Pass your API token as a Bearer header or query parameter:

  • Header (recommended): Authorization: Bearer your-token-here
  • Query parameter: ?token=your-token-here

Client Setup

Claude.ai supports MCP servers via custom connectors. Since the connector form only accepts a URL, pass your token as a query parameter:

  1. Go to Settings > Connectors in Claude.ai.
  2. Click Add custom connector.
  3. Enter a name (e.g., Browserless) and the following URL:
https://mcp.browserless.io/mcp?token=your-token-here
  1. Click Add.

Replace your-token-here with your Browserless API token from the account dashboard.

tip

Clients that support OAuth can connect without a token - the server will prompt you to sign in with your Browserless account.

Regional Endpoints

By default, the hosted MCP server connects to the US West (San Francisco) Browserless region. To use a different region, pass the endpoint as a header or query parameter:

RegionEndpoint
US West — San Francisco (default)https://production-sfo.browserless.io
Europe — Londonhttps://production-lon.browserless.io
Europe — Amsterdamhttps://production-ams.browserless.io

Using the x-browserless-api-url header (for clients that support headers):

{
"mcpServers": {
"browserless": {
"url": "https://mcp.browserless.io/mcp",
"headers": {
"Authorization": "Bearer your-token-here",
"x-browserless-api-url": "https://production-sfo.browserless.io"
}
}
}
}

Using the browserlessUrl query parameter (for URL-only clients like Claude.ai):

https://mcp.browserless.io/mcp?token=your-token-here&browserlessUrl=https://production-sfo.browserless.io

Tools

The MCP server exposes nine tools to your AI assistant, split across two reference pages:

Browser Agent

A single stateful tool, browserless_agent, that drives a browser session across turns. The session persists across tool calls, so the model can navigate, snapshot the page, click, type, fill forms, and react to what it sees — all within one browser context. Ideal for logins, multi-step flows, and anything that needs the browser's state to survive between turns.

REST API Tools

Eight stateless tools that wrap individual Browserless REST endpoints — one call in, one result out:

ToolPurpose
browserless_smartscraperScrape any URL with cascading strategies (HTTP → proxy → headless → CAPTCHA solving)
browserless_functionRun custom Puppeteer JavaScript on the Browserless cloud
browserless_downloadTrigger and retrieve browser-initiated file downloads
browserless_exportExport a page as HTML, PDF, image, or full offline ZIP
browserless_searchWeb/news/image search with optional scraping of each result
browserless_mapDiscover all URLs on a site via sitemap and link extraction
browserless_performanceRun a Lighthouse audit (accessibility, performance, SEO, PWA, best practices)
browserless_crawlCrawl a site from a seed URL and scrape every discovered page

Further Reading