📌Overview

Purpose: The Hyperbrowser MCP Server is designed to facilitate the scraping, extraction, and structuring of data from webpages while providing access to various browser agents.

Overview: This server implements the Model Context Protocol (MCP) to offer tools that enable users to efficiently navigate and interact with web content. Via simple commands, users can harness the power of automation and data extraction in a user-friendly manner.

Key Features:

Webpage Scraping: Extracts formatted content from any webpage, including markdown and screenshots, making data retrieval straightforward.
Web Crawling: Navigates through linked pages to gather LLM-friendly formatted content, enhancing the depth of data collection.
Structured Data Extraction: Converts unorganized HTML into structured JSON, improving the usability of the retrieved data.
Bing Search Integration: Allows querying of the web and retrieves results, expanding the server's functionality beyond local data.
Automation Agents: Supports various browser automation scenarios using agents like OpenAI's CUA and Claude's Computer Use, providing flexibility for complex tasks.

Hyperbrowser MCP Server

This is Hyperbrowser's Model Context Protocol (MCP) Server. It provides tools to scrape, extract structured data, and crawl webpages. The server offers easy access to general-purpose browser agents such as OpenAI's CUA and Anthropic's Claude Computer Use.

For more information, visit the Hyperbrowser Documentation or learn about the Model Context Protocol.

Installation
Usage
Tools
License

Installation

Manual Installation

To install the server, run:

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

Running on Cursor

Add to ~/.cursor/mcp.json:

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

Running on Windsurf

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

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

Development

Clone the repository:

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

Install dependencies:

npm install # or yarn install
npm run build

Run the server:
```
node dist/server.js
```

Tools

scrape_webpage: Extract formatted content from any webpage
crawl_webpages: Navigate through multiple linked pages and extract LLM-friendly content
extract_structured_data: Convert messy HTML into structured JSON
search_with_bing: Query the web with Bing search
browser_use_agent: Lightweight browser automation
openai_computer_use_agent: General-purpose automation using OpenAI’s model
claude_computer_use_agent: Complex browser tasks using Claude

Installing via Smithery

To install Hyperbrowser MCP Server automatically via Smithery:

npx -y @smithery/cli install @hyperbrowserai/mcp --client claude

License

This project is licensed under the MIT License.

mcp