MCP Server

The Browserless MCP server lets AI assistants scrape any webpage through the Model Context Protocol. Connect Claude Desktop, Cursor, VS Code, Windsurf, or any MCP-compatible client to the hosted server and start scraping without managing infrastructure.

Prerequisites

An active Browserless API token (available in your account dashboard)
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

Authenticate by passing your API token as a Bearer header or as a ?token= query parameter. No installation or environment variables required.

Client Setup

Claude.ai
Claude Desktop
Cursor
VS Code
Windsurf

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

Go to Settings > Connectors in Claude.ai.
Click Add custom connector.
Enter a name (e.g., Browserless) and the following URL:

https://mcp.browserless.io/mcp?token=your-token-here

Click Add.

Add to your claude_desktop_config.json:

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

Add to your Cursor MCP settings:

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

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

{
  "mcp": {
    "servers": {
      "browserless": {
        "type": "http",
        "url": "https://mcp.browserless.io/mcp",
        "headers": {
          "Authorization": "Bearer your-token-here"
        }
      }
    }
  }
}

Add to your Windsurf MCP configuration:

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

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

Authentication methods

The server accepts your API token in two ways:

Authorization header (recommended) — Authorization: Bearer your-token-here
token query parameter — ?token=your-token-here

When both are present, the header takes precedence. Use the query parameter for clients that only accept a URL (like Claude.ai custom connectors).

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

Tool: `browserless_smartscraper`

Once connected, your AI assistant gets access to the Smart Scraper tool. It scrapes any webpage using cascading strategies — HTTP fetch, proxy, headless browser, and CAPTCHA solving — automatically selecting the best approach.

Parameters

Parameter	Type	Required	Default	Description
`url`	string	Yes	—	The URL to scrape (http or https)
`formats`	string[]	No	`["markdown"]`	Output formats: `markdown`, `html`, `screenshot`, `pdf`, `links`
`timeout`	number	No	`30000`	Request timeout in milliseconds

Output Formats

markdown — Page content converted to clean Markdown (default)
html — Raw HTML of the page
screenshot — Full-page screenshot as a PNG image
pdf — PDF rendering of the page
links — All links found on the page

Example Usage

Ask your AI assistant to scrape a page:

Scrape https://example.com and summarize the content.

Request multiple formats:

Take a screenshot and extract all links from https://example.com.

Resources

The MCP server also exposes these resources that your AI assistant can read:

Resource	Description
`browserless://api-docs`	Smart Scraper API documentation and parameter reference
`browserless://status`	Live status of the Browserless API connection

Prompt Templates

Built-in prompt templates help your AI assistant use the scraper effectively:

Prompt	Description
`scrape-url`	Scrape a webpage and summarize its content
`extract-content`	Extract specific information from a webpage using custom instructions

Prerequisites​

Hosted Server​

Client Setup​

Regional Endpoints​

Tool: browserless_smartscraper​

Parameters​

Output Formats​

Example Usage​

Resources​

Prompt Templates​

Further Reading​