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

# Bright Data integration for LuumenAI

Collect web data at scale, with each billable job previewed before it runs

## What LuumenAI can do with Bright Data

LuumenAI connects to Bright Data with an API token and exposes 22 tools (15 read-only · 7 write). 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: 22 tools (15 read-only · 7 write)
- Plan: available on all plans
- Category: Databases & data platforms

## About Bright Data with LuumenAI

Connect Bright Data and your agent can check zone bandwidth, costs, and account balance, browse the dataset marketplace, and pull results from finished snapshots and searches. Jobs that spend money — crawls, filtered snapshots, SERP searches, Deep Lookup requests — are held for your approval first, with the scope stated up front.

## Example tools

Read-only (15 in total):

- `BRIGHTDATA_DATASET_LIST` — List pre-built datasets in Bright Data's marketplace for structured scraping.
- `BRIGHTDATA_GET_CUSTOMER_BALANCE` — Get current and pending Bright Data account balances.
- `BRIGHTDATA_GET_DEEP_LOOKUP_RESULTS` — Retrieve enriched records plus available progress, cost, and provider metadata for a completed Deep Lookup request.
- `BRIGHTDATA_GET_DEEP_LOOKUP_STATUS` — Check a Deep Lookup request's status, progress, cost, and provider metadata.
- `BRIGHTDATA_GET_LIST_OF_AVAILABLE_CITIES` — List static-network cities available for a country and proxy pool type.
- `BRIGHTDATA_GET_LIST_OF_AVAILABLE_COUNTRIES` — List country codes available for each static proxy zone type.
- `BRIGHTDATA_GET_SERP_RESULTS` — Retrieve JSON or raw results for an asynchronous BRIGHTDATA_SERP_SEARCH request.
- `BRIGHTDATA_GET_SNAPSHOT_RESULTS` — Download a completed dataset snapshot.

Write and destructive (7 in total, approval required by default):

- `BRIGHTDATA_CRAWL_API` — Start an asynchronous dataset or site crawl.
- `BRIGHTDATA_CREATE_SAFE_ZONE` — Create a durable SERP API or Scraping Browser zone using a fixed safe plan.
- `BRIGHTDATA_FILTER_DATASET` — Create a billable filtered marketplace-dataset snapshot.
- `BRIGHTDATA_SCRAPE_DATA_SYNC` — Scrape up to 20 input objects synchronously.
- `BRIGHTDATA_SEARCH_WEB_ARCHIVE` — Search Bright Data's Web Archive and estimate matching files, dump size in bytes, and dump cost in USD.
- `BRIGHTDATA_SERP_SEARCH` — Submit an asynchronous SERP search and return its response_id.
- `BRIGHTDATA_START_DEEP_LOOKUP` — Start an asynchronous Deep Lookup research request and return its request_id.

## Frequently asked questions

### How does LuumenAI connect to Bright Data?

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 Bright Data on its own?

Read actions answer immediately. Anything that writes is shown as a plan and requires approval by default. Administrators configure that per tool.

### Is there an audit trail?

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

Full page: https://www.luumen.ai/integrations/bright-data/