See what your phantoms are doing, and stop the one that is stuck
Connect PhantomBuster and Luumen can read your agents, their run history, and the console output of any container without leaving the terminal. When a scrape hangs or an agent runs past its window, you see the progress and messages first, then abort the run as an approved step. Luumen authenticates with an API key.
53 tools: 26 read, 27 write. Reads answer instantly. Writes require approval by default. Everything is logged.
What a governed PhantomBuster 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 — abort agent (v1), delete agent, delete lead objects, delete many leads, and more — is shown as a plan and requires approval by default, including the 8 actions classified as destructive. 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 PhantomBuster — 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.