Read review queues and wordlists, then apply moderation changes as approved steps
Connect Moderation API and your team can ask about the state of moderation without opening the dashboard. Check what is sitting in a review queue, read a wordlist, see which actions the organization has available, and confirm plan and quota. Changes — editing words, resolving items, running an action against content or an author — are previewed and held for approval first.
11 tools: 6 read, 5 write. Reads answer instantly. Writes require approval by default. Everything is logged.
What a governed Moderation API 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 — evaluate content without storage, execute moderation action, modify wordlist words, set review queue item status, and more — is shown as a plan and requires approval by default, including the 1 action 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 Moderation API — 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.