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:

Method	Best for
OAuth (Browserless account login)	Clients that support OAuth — no token needed
Authorization header	Clients that support custom headers
token query parameter	URL-only clients (e.g. Claude.ai custom connectors)

When multiple methods are present, they are evaluated in this order: Authorization header (plain API token) → 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_API_TOKEN_HERE
• Query parameter: ?token=YOUR_API_TOKEN_HERE

Client Setup

Claude.ai

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 Customize > 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_API_TOKEN_HERE

4. Click Add.

Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "browserless": {
      "type": "http",
      "url": "https://mcp.browserless.io/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_TOKEN_HERE"
      }
    }
  }
}

Claude Code

Run in your terminal:

claude mcp add --transport http browserless https://mcp.browserless.io/mcp \
  --header "Authorization: Bearer YOUR_API_TOKEN_HERE"

For more information, see the Claude Code MCP documentation.

Cursor

Add to your Cursor MCP settings:

{
  "mcpServers": {
    "browserless": {
      "type": "http",
      "url": "https://mcp.browserless.io/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_TOKEN_HERE"
      }
    }
  }
}

VS Code

Add to your VS Code settings (settings.json):

{
  "mcp": {
    "servers": {
      "browserless": {
        "type": "http",
        "url": "https://mcp.browserless.io/mcp",
        "headers": {
          "Authorization": "Bearer YOUR_API_TOKEN_HERE"
        }
      }
    }
  }
}

Windsurf

Add to your Windsurf MCP configuration:

{
  "mcpServers": {
    "browserless": {
      "type": "http",
      "url": "https://mcp.browserless.io/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_TOKEN_HERE"
      }
    }
  }
}

tip

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

Run Locally

Requirements

Node.js 24 or newer.

Prefer not to use the hosted server? The MCP server is published to npm as @browserless.io/mcp, so you can run it locally with npx — no cloning, building, or Docker required. This is useful for pinning a specific server version or pointing at a self-hosted Browserless instance — including fully air-gapped setups, but only when that self-hosted instance also runs inside the isolated network. On its own, running locally with npx still calls the Browserless cloud for browser execution.

Running locally still calls the Browserless cloud (or your self-hosted instance) for the actual browser work. Only the MCP server process runs on your machine.

stdio (MCP clients)

For desktop MCP clients, point the server config at npx and pass your token as an environment variable. The server starts in stdio mode by default, which is what local clients expect:

Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "browserless": {
      "command": "npx",
      "args": ["-y", "@browserless.io/mcp"],
      "env": {
        "BROWSERLESS_TOKEN": "YOUR_API_TOKEN_HERE"
      }
    }
  }
}

Cursor

Add to your Cursor MCP settings:

{
  "mcpServers": {
    "browserless": {
      "command": "npx",
      "args": ["-y", "@browserless.io/mcp"],
      "env": {
        "BROWSERLESS_TOKEN": "YOUR_API_TOKEN_HERE"
      }
    }
  }
}

VS Code

Add to your VS Code settings (settings.json):

{
  "mcp": {
    "servers": {
      "browserless": {
        "command": "npx",
        "args": ["-y", "@browserless.io/mcp"],
        "env": {
          "BROWSERLESS_TOKEN": "YOUR_API_TOKEN_HERE"
        }
      }
    }
  }
}

Claude Code

Run in your terminal:

claude mcp add browserless --env BROWSERLESS_TOKEN=YOUR_API_TOKEN_HERE \
  -- npx -y @browserless.io/mcp

HTTP (httpStream)

To run the server as a long-lived HTTP endpoint (for example to share one instance across clients) set TRANSPORT=httpStream:

TRANSPORT=httpStream PORT=8080 BROWSERLESS_TOKEN=YOUR_API_TOKEN_HERE \
  npx -y @browserless.io/mcp

Then point your MCP client at http://localhost:8080/mcp, using the same header or query-parameter auth as the hosted server.

Environment variables

Variable	Required	Default	Description
BROWSERLESS_TOKEN	Yes	—	Your Browserless API token
BROWSERLESS_API_URL	No	https://production-sfo.browserless.io	API endpoint (set this to point at a self-hosted instance or a different region)
TRANSPORT	No	stdio	Transport type: stdio or httpStream
PORT	No	8080	HTTP server port (only used with httpStream)
BROWSERLESS_TIMEOUT	No	30000	Request timeout in milliseconds
BROWSERLESS_MAX_RETRIES	No	3	Max retry attempts for failed requests
BROWSERLESS_CACHE_TTL	No	60000	Cache TTL in milliseconds (0 to disable)

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:

Region	Endpoint
US West — San Francisco (default)	https://production-sfo.browserless.io
Europe — London	https://production-lon.browserless.io
Europe — Amsterdam	https://production-ams.browserless.io

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

{
  "mcpServers": {
    "browserless": {
      "type": "http",
      "url": "https://mcp.browserless.io/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_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_API_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:

Tool	Purpose
browserless_smartscraper	Scrape any URL with cascading strategies (HTTP → proxy → headless → CAPTCHA solving)
browserless_function	Run custom Puppeteer JavaScript on the Browserless cloud
browserless_download	Trigger and retrieve browser-initiated file downloads
browserless_export	Export a page as HTML, PDF, image, or full offline ZIP
browserless_search	Web/news/image search with optional scraping of each result
browserless_map	Discover all URLs on a site via sitemap and link extraction
browserless_performance	Run a Lighthouse audit (accessibility, performance, SEO, PWA, best practices)
browserless_crawl	Crawl a site from a seed URL and scrape every discovered page

Further Reading

• Browser Agent — the stateful, multi-turn browserless_agent tool
• REST API Tools — the eight stateless MCP tools
• Browserless Account Dashboard - Get your API token
• REST APIs — Direct REST API access
• BrowserQL — GraphQL-based browser automation
• MCP Overview — Compare Browserless MCP servers
• AI Integrations — Other AI platform integrations