Hyperbrowser MCP Server

What is Hyperbrowser MCP Server about?

Provides a Model Context Protocol (MCP) server that exposes a suite of utilities for web‑scraping, crawling, structured data extraction, and browser‑based automation. It also acts as a bridge to LLM‑driven agents (OpenAI CUA, Claude Computer Use) enabling complex web interactions from any MCP‑compatible client.

How to use Hyperbrowser MCP Server?

1. Installation – Run the package directly with npm:

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

2. Running in development – Clone the repo, install dependencies, build, and start the server:

   git clone git@github.com:hyperbrowserai/mcp.git hyperbrowser-mcp
   cd hyperbrowser-mcp
   npm install   # or yarn install
   npm run build
   node dist/server.js
   

3. Configure for client tools – Add a JSON entry to the client’s MCP configuration (e.g., Cursor, Windsurf, Claude Desktop):

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

4. Invoke tools – Use the defined MCP methods (scrape_webpage, crawl_webpages, extract_structured_data, search_with_bing, browser_use_agent, openai_computer_use_agent, claude_computer_use_agent, create_profile, delete_profile, list_profiles).

Key Features

• Scrape Webpage – Returns markdown, screenshots, and other formatted content.
• Crawl Webpages – Traverses linked pages and aggregates LLM‑friendly output.
• Extract Structured Data – Converts messy HTML into clean JSON structures.
• Bing Search – Performs web queries via Bing.
• Browser Use Agent – Fast, lightweight automation using the generic Browser Use model.
• OpenAI Computer Use Agent – Full‑featured automation with OpenAI’s CUA.
• Claude Computer Use Agent – Complex browser tasks powered by Anthropic’s Claude.
• Profile Management – Create, list, and delete persistent Hyperbrowser profiles.
• Easy CLI Installation – Single‑command setup with npx.
• Smithery Integration – One‑click install for Claude Desktop via Smithery.

Use Cases

• Automating data collection pipelines for research or market analysis.
• Building LLM‑driven assistants that need up‑to‑date web information.
• Enriching knowledge bases with structured JSON extracted from HTML sources.
• Performing automated web testing or UI interaction scripting.
• Integrating Bing search results into AI chat applications.

FAQ

Q: Do I need an API key? A: Yes, a Hyperbrowser API key is required and must be provided via the HYPERBROWSER_API_KEY environment variable.

Q: Can I run the server locally? A: Absolutely. Follow the development steps to start the server from source code.

Q: Which agents are supported? A: OpenAI’s Computer Use, Anthropic’s Claude Computer Use, and the generic Browser Use agent.

Q: How does the server integrate with existing MCP clients? A: By adding the mcpServers entry (shown above) to the client’s configuration file, the client can call any of the exposed methods.

Q: Is there a license? A: The project is licensed under the MIT License.

Hyperbrowser MCP Server

This is Hyperbrowser's Model Context Protocol (MCP) Server. It provides various tools to scrape, extract structured data, and crawl webpages. It also provides easy access to general purpose browser agents like OpenAI's CUA, Anthropic's Claude Computer Use, and Browser Use.

More information about the Hyperbrowser can be found here. The hyperbrowser API supports a superset of features present in the mcp server.

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

Table of Contents

• Installation
• Usage
• Tools
• Configuration
• License

Installation

Manual Installation

To install the server, run:

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

Running on Cursor

Add to ~/.cursor/mcp.json like this:

{
  "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 like this:

{
  "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 app

This is an example config for the Hyperbrowser MCP server for the Claude Desktop client.

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

Tools

• scrape_webpage - Extract formatted (markdown, screenshot etc) content from any webpage
• crawl_webpages - Navigate through multiple linked pages and extract LLM-friendly formatted content
• extract_structured_data - Convert messy HTML into structured JSON
• search_with_bing - Query the web and get results with Bing search
• browser_use_agent - Fast, lightweight browser automation with the Browser Use agent
• openai_computer_use_agent - General-purpose automation using OpenAI’s CUA model
• claude_computer_use_agent - Complex browser tasks using Claude computer use
• create_profile - Creates a new persistent Hyperbrowser profile.
• delete_profile - Deletes an existing persistent Hyperbrowser profile.
• list_profiles - Lists existing persistent Hyperbrowser profiles.

Installing via Smithery

To install Hyperbrowser MCP Server for Claude Desktop automatically via Smithery:

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

Resources

The server provides the documentation about hyperbrowser through the resources methods. Any client which can do discovery over resources has access to it.

License

This project is licensed under the MIT License.