Read Convex projects and deployments, then make changes as approved steps
Connect Convex and your agent can see the shape of your backend: which projects a team owns, what deployments sit under each one, which deploy keys exist, and how log streams are configured. It reads that on request and answers right away. Changes like creating a deployment or issuing a deploy key are previewed first and go out as approved, audited steps.
19 tools: 12 read, 7 write. Reads answer instantly. Writes require approval by default. Everything is logged.
What a governed Convex 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 deploy key, create deployment, create project, delete custom domain, 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 Convex — 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.