Read your Lucid diagrams for context, and draft new ones as approved steps.
Your architecture lives in Lucid. Luumen reads it: document metadata, folder contents, comment threads, and the text inside a diagram. Ask what a service talks to during an incident and get the answer from the picture your team already maintains. When something needs to change or a new diagram needs to exist, Luumen shows the plan first and waits for your approval. Connected with OAuth via dynamic client registration.
35 tools: 13 read, 22 write. Reads answer instantly. Writes require approval by default. Everything is logged.
What a governed Lucid MCP run looks like inside Luumen.
Authorize once with OAuth 2.0. 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 — lucid add block, lucid add dynamic table, lucid add items to dynamic table, lucid add line, and more — is shown as a plan and requires approval by default, including the 5 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 Lucid MCP — 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.