Collect web data at scale, with each billable job previewed before it runs
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.
22 tools: 15 read, 7 write. Reads answer instantly. Writes require approval by default. Everything is logged.
What a governed Bright Data run looks like inside Luumen.
Authorize once with API token. Luumen lists the scopes each action needs before you approve the connection, and credentials never appear in the chat.
Read actions answer immediately. Anything that writes — start site crawl, create safe zone, filter dataset, scrape data synchronously, and more — is shown as a plan and requires approval by default. Administrators configure that per tool, so you decide exactly which actions can ever run unattended.
You decide. Actions are granted per agent, skill, and team, and per environment — production is not staging. Read access can be broad while writes stay narrow.
Every call to Bright Data — read or write, approved or declined — is recorded with the actor, the input, and the result, and can be linked to the ticket or change record.
Connect in minutes. Every action scoped, approved, and audited from day one.