Read team notes for context, and draft new ones as approved steps
Connect HackMD and your runbooks, incident notes, and team docs become context the agent can read directly. Ask what a procedure says, find the folder a postmortem belongs in, or check what is sitting in trash. When the agent writes a note, moves one to trash, or restores one, it shows you the change first and waits for approval.
8 tools: 5 read, 3 write. Reads answer instantly. Writes require approval by default. Everything is logged.
What a governed HackMD 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 note, move note to trash, restore notes — 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 HackMD — 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.