Skip to main content

​
Overview

The Hyperbrowser MCP server provides a standardized interface for AI models to access powerful web automation capabilities like scraping, structured extraction, and crawling. You can find the server implementation on GitHub: hyperbrowserai/mcp. With the Hyperbrowser MCP, Claude can browse the web With the Hyperbrowser MCP, Claude can browse the web.

​
Installation

​
Prerequisites

  • Node.js (v14 or later)
  • npm or yarn

​
Setup

  1. Install the Hyperbrowser MCP server:
npx hyperbrowser-mcp

​
Configuration

​
Client Setup

Configure your MCP client to launch the Hyperbrowser MCP server: 
{
  "mcpServers": {
    "hyperbrowser": {
      "command": "npx",
      "args": ["hyperbrowser-mcp"],
      "env": {
        "HYPERBROWSER_API_KEY": "your-api-key"
      }
    }
  }
}

​
Alternative: Shell Script Wrapper

For clients that don’t support an env field (for example, Cursor): 
{
  "mcpServers": {
    "hyperbrowser": {
      "command": "bash",
      "args": ["/path/to/hyperbrowser-mcp/run_server.sh"]
    }
  }
}
Create run_server.sh and add your API key: 
#!/bin/bash
export HYPERBROWSER_API_KEY="your-api-key"
npx hyperbrowser-mcp

​
Tools

​
Scrape Webpage

Retrieve content from a URL in various formats.
  • Method: scrape_webpage
  • Parameters:
    • url: string – The URL to scrape
    • outputFormat: string[] – Output formats (markdown, html, links, screenshot)
    • apiKey: string (optional) – API key override
    • sessionOptions: object (optional) – Browser session configuration
Example: 
{
  "url": "https://example.com",
  "outputFormat": ["markdown", "screenshot"],
  "sessionOptions": {
    "useStealth": true,
    "acceptCookies": true
  }
}

​
Extract Structured Data

Extract data from webpages according to a prompt and optional schema.
  • Method: extract_structured_data
  • Parameters:
    • urls: string[] – URLs to extract from (supports wildcards)
    • prompt: string – Instructions for extraction
    • schema: object (optional) – JSON schema for extracted data
    • apiKey: string (optional) – API key override
    • sessionOptions: object (optional) – Browser session configuration
Example: 
{
  "urls": ["https://example.com/products/*"],
  "prompt": "Extract product name, price, and description",
  "schema": {
    "type": "object",
    "properties": {
      "name": { "type": "string" },
      "price": { "type": "number" },
      "description": { "type": "string" }
    }
  },
  "sessionOptions": {
    "useStealth": true
  }
}

​
Crawl Webpages

Navigate through multiple pages on a site, optionally following links.
  • Method: crawl_webpages
  • Parameters:
    • url: string – Starting URL
    • outputFormat: string[] – Desired output formats
    • followLinks: boolean – Whether to follow links
    • maxPages: number (default: 10) – Max pages to crawl
    • ignoreSitemap: boolean (optional) – Skip the site’s sitemap
    • apiKey: string (optional) – API key override
    • sessionOptions: object (optional) – Browser session configuration
Example: 
{
  "url": "https://example.com",
  "outputFormat": ["markdown", "links"],
  "followLinks": true,
  "maxPages": 5,
  "sessionOptions": {
    "acceptCookies": true
  }
}

​
Session Options

All tools support these common session configuration options:
  • useStealth: boolean – Make browser detection more difficult
  • useProxy: boolean – Route traffic through proxies
  • solveCaptchas: boolean – Automatically solve CAPTCHA challenges
  • acceptCookies: boolean – Automatically handle cookie consent popups