Read your AppDrag backend data, then run function calls as approved steps
Connect AppDrag and Luumen can query your Cloud Backend directly from the terminal. Run Visual SQL SELECT statements against your database, call production API functions over GET, and see the results inline. When a change is needed — an update to a table, a POST or PUT against a function — Luumen shows the call first and waits for your approval. Authentication uses an API key.
11 tools: 2 read, 9 write. Reads answer instantly. Writes require approval by default. Everything is logged.
What a governed AppDrag 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 — execute cloud backend function via delete, execute preprod function (delete), execute dev function (patch), execute cloud backend function via post, 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 AppDrag — 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.