Hyperbrowser

🚀 Hyperbrowser MCP Server

The Hyperbrowser's Model Context Protocol (MCP) server offers various tools for web scraping, structured data extraction, and crawling. It also provides convenient access to general browser agents like OpenAI's CUA, Anthropic's Claude Computer Use, and Browser Use.

More information about Hyperbrowser can be found here. The Hyperbrowser API supports a superset of all the features of the MCP server.

More information about the Model Context Protocol can be found here.

🚀 Quick Start

This is the Hyperbrowser's Model Context Protocol (MCP) server, which provides a variety of tools for web scraping, structured data extraction, and crawling. It also offers easy access to general browser agents such as OpenAI's CUA, Anthropic's Claude Computer Use, and Browser Use.

📦 Installation

Manual Installation

To install the server, run:

npx hyperbrowser-mcp <YOUR-HYPERBROWSER-API-KEY>

Run on Cursor

Add the following to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "hyperbrowser": {
      "command": "npx",
      "args": ["-y", "hyperbrowser-mcp"],
      "env": {
        "HYPERBROWSER_API_KEY": "YOUR-API-KEY"
      }
    }
  }
}

Run on Windsurf

Add the following to your ./codeium/windsurf/model_config.json:

{
  "mcpServers": {
    "hyperbrowser": {
      "command": "npx",
      "args": ["-y", "hyperbrowser-mcp"],
      "env": {
        "HYPERBROWSER_API_KEY": "YOUR-API-KEY"
      }
    }
  }
}

Development

For development purposes, you can run the server directly from the source code.

1. Clone the repository:

   git clone git@github.com:hyperbrowserai/mcp.git hyperbrowser-mcp
   cd hyperbrowser-mcp
   

2. Install dependencies:

   npm install # or yarn install
   npm run build
   

3. Run the server:

   node dist/server.js
   

Claude Desktop Application

Here is an example of configuring the Hyperbrowser MCP server for the Claude Desktop client.

{
  "mcpServers": {
    "hyperbrowser": {
      "command": "npx",
      "args": ["--yes", "hyperbrowser-mcp"],
      "env": {
        "HYPERBROWSER_API_KEY": "your-api-key"
      }
    }
  }
}

💻 Usage Examples

Tools

• scrape_webpage - Extract formatted content (Markdown, screenshots, etc.) from any web page.
• crawl_webpages - Traverse multiple linked pages and extract content suitable for LLM processing.
• extract_structured_data - Convert messy HTML into structured JSON.
• search_with_bing - Query the web using the Bing search engine.
• browser_use_agent - Lightweight browser automation using the Browser Use agent.
• openai_computer_use_agent - General automation using OpenAI's CUA model.
• claude_computer_use_agent - Perform complex browser tasks using Claude Computer Use.
• hyperbrowser-mcp - Hyperbrowser's MCP implementation for advanced use cases.

📚 Documentation

To configure MCP, refer to here.

📄 License

Please refer to the license file in the project repository.