See what your Cursor cloud agents are doing, without leaving the terminal
Connect Cursor with an API key and ask about your cloud agents in plain language. CURSOR_LIST_AGENTS shows what is running. CURSOR_GET_AGENT_CONVERSATION pulls the full history for one of them. CURSOR_LIST_REPOSITORIES and CURSOR_LIST_MODELS cover the repos and models in reach, and CURSOR_GET_ME confirms which key you are on. All five are read-only, so answers come back right away and nothing in Cursor changes.
5 tools, all read-only. They answer instantly, and every call is logged.
Authorize once with API token. Luumen lists the scopes each action needs before you approve the connection, and credentials never appear in the chat.
No. Every one of the 5 tools LuumenAI has for Cursor is read-only, so it can answer questions from Cursor but cannot change anything in it. Reads are not gated — they answer immediately, and each one is recorded on the audit trail with the actor and the result.
You decide. Access is granted per agent, skill, and team, and per environment — production is not staging.
Every call to Cursor 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.