Read Manus tasks and projects, then create or update work as approved steps
Connect Manus and the agent can see your automation work without you opening the dashboard: which tasks ran, what they output, how many credits they used, which projects they belong to, and what files are attached. When something needs to change — a new task, a project, a webhook — the agent shows the exact call first and waits for your approval. Authentication is by API key.
14 tools: 6 read, 8 write. Reads answer instantly. Writes require approval by default. Everything is logged.
What a governed Manus 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 — create file, create new project, create new task, create webhook, and more — is shown as a plan and requires approval by default, including the 3 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 Manus — 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.