Hyperbrowser MCP Server

Browser AutomationTypeScript

A browser automation server for web scraping, data extraction, and web crawling

Available Tools

browse_website

Navigates to a specified URL and returns the page content

extract_from_website

Extracts structured data from a website using a specified schema

search_website

Searches a website for specific content

crawl_website

Crawls a website and returns data from multiple pages

create_hyperbrowser_profile

Creates a new browser profile for session management

delete_hyperbrowser_profile

Deletes an existing browser profile

list_hyperbrowser_profiles

Lists all available browser profiles

Hyperbrowser provides powerful tools for web automation, allowing you to scrape websites, extract structured data, and crawl web pages efficiently. It integrates with general purpose browser agents like OpenAI's CUA, Anthropic's Claude Computer Use, and Browser Use. The server implements the Model Context Protocol (MCP) specification, making it compatible with various AI assistants and tools. With Hyperbrowser, you can automate complex web interactions, gather data at scale, and build sophisticated web automation workflows.

Installation

You can install the Hyperbrowser MCP server using npm:

npm install @hyperbrowserai/mcp

Running the Server

There are multiple ways to run the Hyperbrowser MCP server:

Using the CLI

After installation, you can run the server directly:

npx @hyperbrowserai/mcp

Using Docker

You can also run the server using Docker:

docker run -p 3000:3000 -e HYPERBROWSER_API_KEY=your_api_key hyperbrowserai/mcp

Configuration

The Hyperbrowser MCP server requires configuration through environment variables:

HYPERBROWSER_API_KEY: Your Hyperbrowser API key (required)
PORT: The port to run the server on (default: 3000)
SERVER_TYPE: The type of server to run (options: "http", "stdio", "sse", default: "http")

You can set these variables in a .env file in your project directory or pass them directly when running the server.

Getting an API Key

To obtain a Hyperbrowser API key:

Visit docs.hyperbrowser.ai
Sign up for an account
Navigate to your account settings to generate an API key

Using with AI Assistants

Hyperbrowser MCP server can be used with various AI assistants that support the Model Context Protocol. The server provides tools for web scraping, data extraction, and browser automation that can be accessed by these assistants.

Profile Management

Hyperbrowser supports profile management, allowing you to create and manage different browser profiles for various tasks. This is useful for maintaining separate sessions, cookies, and settings for different automation tasks.

You can create profiles, list existing profiles, and delete profiles using the provided tools. When using browser automation tools, you can specify which profile to use by including the profileId in the sessionOptions parameter.