Launch cited research and enrichment runs, then check status and pull results
Parallel Task MCP gives your agent a way to run deep research without leaving the terminal. Ask a question that needs real sources, and Luumen opens a task, watches its status, and returns the finished write-up as markdown with citations. Batch enrichment works the same way. Luumen connects over DCR OAuth, reads status and results on demand, and holds task creation for your approval by default.
4 tools: 2 read, 2 write. Reads answer instantly. Writes require approval by default. Everything is logged.
What a governed Parallel Task 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 — createdeepresearch, createtaskgroup — is shown as a plan and requires approval by default. 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 Parallel Task 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.