1. Home
  2. Servers
  3. Browser Automation
  4. Hyperbrowser MCP Server

Server profile

Hyperbrowser MCP Server

Hyperbrowser MCP Server combines web scraping, crawling, structured extraction, and cloud browser agents. Assistants can choose Browser Use, OpenAI computer use, or Claude computer use and manage persistent profiles.

View repositoryInstall & configure

Server facts

Hyperbrowser MCP Server

Project

Author
hyperbrowserai
Repository
github.com/hyperbrowserai/mcp
License
MIT
Category
Browser Automation

Tech

Runtime / language
node
Transports
stdio
Remote available
No
Authentication
Not specified

Activity

GitHub stars
789
Last commit
Data as of

Tags

  • Browser Agents
  • Browser Profiles
  • Structured Extraction
  • Web Crawling
  • Web Scraping

Overview

Hyperbrowser MCP Server gives assistants both content-retrieval tools and access to cloud browser agents. A single-page scraper returns content in formats such as Markdown or screenshots, while the crawler follows linked pages to gather material across a site. Schema-based extraction converts page content into structured data, and a Bing search tool adds web discovery. These operations support workflows that need page content or structured records without requiring every task to be expressed as a series of browser interactions. The README notes that the underlying Hyperbrowser API offers more features than the MCP server, so the exposed tools should not be assumed to cover the entire service.

For interactive tasks, the integration provides Browser Use, OpenAI computer use, and Claude computer use agents. The supplied tool descriptions distinguish a lightweight option for explicit instructions from agents intended for more general or complex interactions. Persistent browser profiles can be created, listed with optional pagination, and deleted. Setup launches the hyperbrowser-mcp npm package through npx and supplies a Hyperbrowser API key in the client configuration. Examples are included for Cursor, Windsurf, and Claude Desktop, with a Smithery installation alternative. Developers can also build a local checkout and run its compiled server. Documentation is exposed through MCP resources for clients that support resource discovery. The project is distributed under the MIT license.

Install & configure

Requirements

  • npx
  • A Hyperbrowser API key
  • An MCP-compatible client
Documented launch / install command
npx -y hyperbrowser-mcp

The README supplies client configurations for Cursor, Windsurf, and Claude Desktop. A source checkout can instead be built with npm and launched from dist/server.js.

Config file · macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

Windows: %APPDATA%\Claude\claude_desktop_config.json

Use Settings → Developer → Edit Config when available. Do not assume a Linux configuration path; check the client documentation for your platform. Remote servers use the app’s connector flow when supported, not the local stdio file shown here. Merge this example with existing settings; do not overwrite unrelated servers.

Claude Desktop configuration
{
  "mcpServers": {
    "mcp-hyperbrowserai": {
      "command": "npx",
      "args": [
        "-y",
        "hyperbrowser-mcp"
      ],
      "env": {
        "HYPERBROWSER_API_KEY": "<Hyperbrowser API key>"
      }
    }
  }
}

Read the Claude Desktop setup guide

Config file · Project: .cursor/mcp.json

User: ~/.cursor/mcp.json

The project path is relative to the workspace root. The tilde denotes your user home directory. Use Cursor’s MCP settings to confirm which configuration and scope your installed version is reading. Merge this example with existing settings; do not overwrite unrelated servers.

Cursor configuration
{
  "mcpServers": {
    "mcp-hyperbrowserai": {
      "command": "npx",
      "args": [
        "-y",
        "hyperbrowser-mcp"
      ],
      "env": {
        "HYPERBROWSER_API_KEY": "<Hyperbrowser API key>"
      }
    }
  }
}

Read the Cursor setup guide

Config file · Workspace: .vscode/mcp.json

For user scope, use the “MCP: Open User Configuration” command if available. Do not guess a user configuration path across operating systems, profiles, containers, or remote workspaces; check the client documentation. Merge this example with existing settings; do not overwrite unrelated servers.

VS Code configuration
{
  "servers": {
    "mcp-hyperbrowserai": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "hyperbrowser-mcp"
      ],
      "env": {
        "HYPERBROWSER_API_KEY": "<Hyperbrowser API key>"
      }
    }
  }
}

Read the VS Code setup guide

Config file · macOS/Linux: ~/.codeium/windsurf/mcp_config.json

Windows: %USERPROFILE%\.codeium\windsurf\mcp_config.json

Open the MCP configuration through Windsurf’s settings when possible to confirm the active file. Paths can differ in managed or future releases; check the client documentation if this location is not present. Merge this example with existing settings; do not overwrite unrelated servers.

Windsurf configuration
{
  "mcpServers": {
    "mcp-hyperbrowserai": {
      "command": "npx",
      "args": [
        "-y",
        "hyperbrowser-mcp"
      ],
      "env": {
        "HYPERBROWSER_API_KEY": "<Hyperbrowser API key>"
      }
    }
  }
}

Read the Windsurf setup guide

Config file · Project scope: .mcp.json at the repository root

The project file uses mcpServers. For user scope, use claude mcp add --scope user rather than assuming .mcp.json in your home directory is the user configuration. Check the client documentation for managed settings and storage details. Merge this example with existing settings; do not overwrite unrelated servers.

Claude Code configuration
{
  "mcpServers": {
    "mcp-hyperbrowserai": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "hyperbrowser-mcp"
      ],
      "env": {
        "HYPERBROWSER_API_KEY": "<Hyperbrowser API key>"
      }
    }
  }
}

Read the Claude Code setup guide

Examples are translated from the published configuration. Supply your own credentials and verify requirements in the upstream README. Remote connectors are shown only where a supported configuration format is known.

Tools

Source: repository tool metadata. Tool descriptions are a documented snapshot, not a live capability check.

ToolWhat it does
scrape_webpageRetrieve one page as text, HTML, links, or screenshots with browser options.
crawl_webpagesCollect content from linked pages starting at a selected URL.
extract_structured_dataExtract webpage information according to a supplied schema.
browser_use_agentRun explicit browser tasks with the Browser Use cloud agent.
openai_computer_use_agentDelegate general browser interactions to OpenAI computer use.
claude_computer_use_agentDelegate complex browser interactions to Claude computer use.
search_with_bingFind web results through Bing.
create_profileCreate a persistent Hyperbrowser profile.
delete_profileRemove a persistent Hyperbrowser profile.
list_profilesList persistent browser profiles with optional pagination.

Names, permissions, and defaults can change. Check the current upstream documentation before granting access.

Use cases

  • Extract page content as Markdown or screenshots
  • Crawl linked pages for content collection
  • Convert webpage content into schema-shaped data
  • Delegate interactive tasks to cloud browser agents
  • Create and manage persistent browser profiles

Strengths

  • Combines retrieval and browser-agent tools in one server
  • Offers three browser-agent integrations
  • Includes schema-based extraction and persistent profiles

Limitations

  • Requires a Hyperbrowser API key
  • The MCP toolset exposes only a subset of Hyperbrowser API features

Frequently asked questions

Browser Use, OpenAI computer use, and Claude computer use are exposed.

Yes. extract_structured_data uses a schema to shape the extracted webpage data.

Yes. The tool list includes creating, listing, and deleting persistent Hyperbrowser profiles.

No. The README says the API includes additional features beyond the MCP server.

Independent listing, not an affiliation or security review. Grant the least access needed and verify the upstream instructions before running code.

Related MCP servers

Playwright MCP

Browser Automation

Playwright MCP lets AI assistants operate browsers using structured accessibility data. It suits agents that need persistent page context, interactive exploration, and browser inspection without a vision model.

nodestdio38,243 GitHub stars

Browserbase MCP Server

Browser Automation

Browserbase MCP Server lets assistants operate cloud browser sessions through Browserbase and Stagehand. Six tools handle sessions, navigation, page actions, observation, and extraction, with hosted and self-hosted connection options.

nodestdio3,399 GitHub stars

BrowserTools MCP

Browser Automation

BrowserTools MCP brings browser logs, screenshots, selected elements, and Lighthouse audits into compatible AI editors. It uses a Chrome extension plus two local servers, and the project is no longer active.

nodestdio7,328 GitHub stars

Playwright MCP Server

Browser Automation

ExecuteAutomation’s Playwright MCP Server lets AI clients automate real browsers, capture screenshots, scrape pages, and generate tests. It also provides device-profile emulation and local stdio or standalone HTTP operation.

nodestdio5,666 GitHub stars

Browser MCP

Browser Automation

Browser MCP combines an MCP server with a Chrome extension to automate your existing browser. It is aimed at AI applications that need local browsing and access to already signed-in sessions.

nodestdio7,189 GitHub stars

Browser Use MCP Server

Browser Automation

Browser Use MCP Server connects AI agents to browser-use for browser control. It supports SSE and proxied stdio connections, asynchronous tasks, and VNC viewing so users can watch browser automation as it happens.

pythonstdio848 GitHub stars