Read Carbon Voice threads for context, then send the follow-up as an approved step.
Carbon Voice holds a lot of decisions that never made it into a ticket. Luumen reads your authorized voice messages, conversations, folders, and AI Action responses to pull that context into the terminal. When something needs to go back out — a reply in a thread, a direct message, a new folder — it previews the change first and waits for your approval. Connection uses DCR OAuth.
28 tools: 16 read, 12 write. Reads answer instantly. Writes require approval by default. Everything is logged.
What a governed Carbon Voice 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 — add attachments to message, create conversation message, create direct message, create folder, and more — 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 Carbon Voice 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.