Hyperbrowser MCP Server

Hyperbrowser MCP Server

What is Hyperbrowser MCP Server about?

Hyperbrowser MCP Server delivers a set of utilities for interacting with the web programmatically. It can fetch and format page content, traverse linked pages, convert messy HTML into structured JSON, perform Bing searches, and invoke powerful browser‑automation agents (OpenAI CUA, Claude Computer Use, and a generic Browser Use agent). All capabilities are exposed through the Model Context Protocol, allowing AI models to call them as remote functions.

How to use Hyperbrowser MCP Server?

1. Install with a single command:

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

2. Configure the MCP client (e.g., Cursor, Windsurf, Claude Desktop) by adding a JSON block that points to the hyperbrowser server, using npx as the command and supplying the API key via an environment variable.
3. Invoke any of the exposed tools (e.g., scrape_webpage, crawl_webpages, search_with_bing, openai_computer_use_agent) from the client’s prompt or programmatic API.

Key features of Hyperbrowser MCP Server

• Scrape Webpages – Return markdown, screenshots, and other formatted content.
• Crawl Multiple Pages – Follow links and collect LLM‑friendly data across a site.
• Extract Structured Data – Transform arbitrary HTML into JSON schemas.
• Bing Search Integration – Perform web searches and retrieve results.
• Browser Automation Agents – Access OpenAI’s CUA, Claude Computer Use, and a lightweight Browser Use agent for complex interactions.
• Profile Management – Create, list, and delete persistent Hyperbrowser profiles.
• Easy Installation – One‑line npx command; supports manual dev setup via npm/yarn.

Use cases of Hyperbrowser MCP Server

• Research assistants that need up‑to‑date information from the web.
• Data pipelines extracting tabular data from product pages or reports.
• Content generation tools that pull source material and format it for LLM consumption.
• Automation scripts that navigate sites, fill forms, or download files using CUA/Claude agents.
• Search‑augmented chatbots that retrieve relevant web results via Bing.

FAQ from the Hyperbrowser MCP Server

Q: Do I need a Hyperbrowser account? A: Yes, an API key from Hyperbrowser is required to authenticate requests.

Q: Can I run the server locally for development? A: Absolutely. Clone the repo, run npm install && npm run build, then start with node dist/server.js.

Q: Which environment variable holds the API key? A: HYPERBROWSER_API_KEY (or the generic placeholder API_KEY in configuration templates).

Q: Is the server compatible with other MCP clients? A: The server follows the standard Model Context Protocol, so any MCP‑compatible client can call its methods.

Q: How are profiles managed? A: Use the create_profile, list_profiles, and delete_profile tools to maintain persistent browsing contexts.

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.