---
title: "Hyperbrowser integration for LuumenAI"
url: "https://www.luumen.ai/integrations/hyperbrowser/"
entity: SoftwareIntegration
category: "Databases & data platforms"
audience: "SRE, DevOps, platform engineering, IT operations"
---

# Hyperbrowser integration for LuumenAI

Fetch pages, run crawls, and drive browser tasks from the terminal

## What LuumenAI can do with Hyperbrowser

LuumenAI connects to Hyperbrowser with an API token and exposes 42 tools (25 read-only · 11 write · 6 destructive). Reads answer immediately; writes are shown as a plan and require approval by default, configurable per tool by an administrator.

## Key facts

- Authentication: API token
- Tools available: 42 tools (25 read-only · 11 write · 6 destructive)
- Plan: available on all plans
- Category: Databases & data platforms

## About Hyperbrowser with LuumenAI

Hyperbrowser gives Luumen a browser it can drive. Fetch a vendor status page as markdown, crawl a docs site, or hand a multi-step click-through to a browser-use task and poll it to completion. Reads come back right away. Starting jobs, creating sessions, and deleting profiles are previewed and held for approval first. Connected with an API key.

## Example tools

Read-only (25 in total):

- `HYPERBROWSER_FETCH_WEB_PAGE` — Fetch a web page and return content in various formats (HTML, Markdown, JSON, screenshot, etc.).
- `HYPERBROWSER_GET_BROWSER_USE_TASK_STATUS` — Retrieve the current status of a browser-use task.
- `HYPERBROWSER_GET_CLAUDE_COMPUTER_USE_TASK_RESULT` — Retrieve the complete result and status of a Claude Computer Use task.
- `HYPERBROWSER_GET_CLAUDE_COMPUTER_USE_TASK_STATUS` — Poll the execution status of a Claude Computer Use task.
- `HYPERBROWSER_GET_CRAWL_JOB_STATUS` — Retrieve the status and results of a specific crawl job.
- `HYPERBROWSER_GET_CRAWL_STATUS` — Retrieve the current status of a specific crawl job.
- `HYPERBROWSER_GET_CUA_TASK_RESULT` — Retrieve the status and results of a CUA (Claude User Agent) task.
- `HYPERBROWSER_GET_CUA_TASK_STATUS` — Poll the execution status of a CUA task.

Write and destructive (17 in total, approval required by default):

- `HYPERBROWSER_ADD_EXTENSION` — Add a new browser extension to Hyperbrowser for use in sessions.
- `HYPERBROWSER_CREATE_PROFILE` — Creates a new persistent Hyperbrowser profile for storing browser state (cookies, sessions, etc.).
- `HYPERBROWSER_CREATE_SCRAPE_JOB` — Initiate a new scrape job.
- `HYPERBROWSER_CREATE_SESSION` — Create a new browser session with custom stealth, proxy, and privacy settings.
- `HYPERBROWSER_DELETE_PROFILE` — Delete a profile.
- `HYPERBROWSER_START_BROWSER_USE_TASK` — Start an asynchronous browser-use task.
- `HYPERBROWSER_START_CLAUDE_COMPUTER_USE_TASK` — Start a Claude Computer Use task.
- `HYPERBROWSER_START_CRAWL_JOB` — Start a new crawl job for a specified URL.

## Frequently asked questions

### How does LuumenAI connect to Hyperbrowser?

Authorize once with API token. Luumen lists the scopes each action needs before you approve the connection, and credentials never appear in the chat.

### Can LuumenAI change things in Hyperbrowser on its own?

Read actions answer immediately. Anything that writes is shown as a plan and requires approval by default, including the 6 actions classified as destructive. Administrators configure that per tool.

### Is there an audit trail?

Every call to Hyperbrowser — read or write, approved or declined — is recorded with the actor, the input, and the result.

Full page: https://www.luumen.ai/integrations/hyperbrowser/