---
title: "Anchor Browser integration for LuumenAI"
url: "https://www.luumen.ai/integrations/anchor-browser/"
entity: SoftwareIntegration
category: "AI & automation"
audience: "SRE, DevOps, platform engineering, IT operations"
---

# Anchor Browser integration for LuumenAI

Drive headless browsers, inspect sessions, and ship automation tasks from the terminal

## What LuumenAI can do with Anchor Browser

LuumenAI connects to Anchor Browser with an API token and exposes 64 tools (25 read-only · 32 write · 7 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: 64 tools (25 read-only · 32 write · 7 destructive)
- Plan: available on all plans
- Category: AI & automation

## About Anchor Browser with LuumenAI

Anchor Browser runs the browser automation behind your web-facing runbooks. Connect it and Luumen can read session state, page lists, rendered page content, and task versions while you work. When a task needs to change — a new draft, a deploy, a fresh profile — Luumen shows the plan first and waits for your approval before writing. Authentication is by API key.

## Example tools

Read-only (25 in total):

- `ANCHOR_BROWSER_COPY_SELECTED_TEXT` — Copy currently selected text in a browser session to the clipboard.
- `ANCHOR_BROWSER_GET_BATCH_SESSION_STATUS` — Retrieve detailed status information for a specific batch including progress and errors.
- `ANCHOR_BROWSER_GET_BROWSER_SESSION` — Retrieve detailed information about a specific browser session.
- `ANCHOR_BROWSER_GET_CLIPBOARD_CONTENT` — Retrieve the current content of the clipboard from a browser session.
- `ANCHOR_BROWSER_GET_LATEST_TASK_VERSION` — Retrieve the latest version of a task including the full base64 encoded code content.
- `ANCHOR_BROWSER_GET_PROFILE2` — Retrieve details of a specific profile by its name.
- `ANCHOR_BROWSER_GET_SESSION_PAGES` — Retrieve all pages associated with a specific browser session.
- `ANCHOR_BROWSER_GET_TASK_DRAFT` — Retrieve the draft version of a task, including the full Base64 encoded code content.

Write and destructive (39 in total, approval required by default):

- `ANCHOR_BROWSER_CLICK_MOUSE` — Perform a mouse click at specified coordinates within a browser session.
- `ANCHOR_BROWSER_CREATE_INTEGRATION` — Create a new integration with a third-party service like 1Password.
- `ANCHOR_BROWSER_CREATE_OR_UPDATE_TASK_DRAFT` — Create or update the draft version of a task.
- `ANCHOR_BROWSER_CREATE_PROFILE` — Creates a new browser profile from an active session.
- `ANCHOR_BROWSER_CREATE_TASK` — Create a new task or update an existing task with the same name.
- `ANCHOR_BROWSER_DELETE_EXTENSION` — Delete a browser extension and remove it from storage.
- `ANCHOR_BROWSER_DELETE_INTEGRATION` — Delete an existing integration and remove its stored credentials.
- `ANCHOR_BROWSER_DELETE_PROFILE` — Delete a browser profile by ID.

## Frequently asked questions

### How does LuumenAI connect to Anchor Browser?

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 Anchor Browser on its own?

Read actions answer immediately. Anything that writes is shown as a plan and requires approval by default, including the 7 actions classified as destructive. Administrators configure that per tool.

### Is there an audit trail?

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

Full page: https://www.luumen.ai/integrations/anchor-browser/
