Hyperbrowser MCP

Add to your client

Copy the config for your MCP client and paste it into its config file.

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

Before you start

• Node.js installed (the server runs via npx)
• A Hyperbrowser API key — sign up at https://app.hyperbrowser.ai and create a key in the dashboard (docs at https://docs.hyperbrowser.ai)
• Set the key as the HYPERBROWSER_API_KEY environment variable (or pass it as a CLI argument)

About Hyperbrowser MCP

Tools & capabilities (10)

When to use it

• Use it when you want an agent to scrape or crawl sites that block ordinary requests, without running your own browser infra.
• Use it when you need clean, structured JSON extracted from messy HTML against a schema.
• Use it when a task requires real clicking/typing/navigation — let a Browser-Use, OpenAI CUA, or Claude computer-use agent drive the page.
• Use it when you need to reuse a logged-in session across runs via persistent profiles.
• Use it when you want web search (Bing) results piped directly into an LLM workflow.

Quick setup

1. 1Get a Hyperbrowser API key from the dashboard at https://app.hyperbrowser.ai.
2. 2Add the server to your MCP client config (e.g. ~/.cursor/mcp.json or claude_desktop_config.json) with command "npx" and args ["-y", "hyperbrowser-mcp"].
3. 3Provide the key via the HYPERBROWSER_API_KEY environment variable in that config.
4. 4Restart your MCP client so it picks up the new server.
5. 5Verify by asking the client to scrape_webpage on a known URL.

Hyperbrowser MCP FAQ