Pull Kaggle datasets and competition files, and publish new versions on approval.
Connect Kaggle and Luumen can read the datasets, files, and competition data your team depends on. Check what a dataset contains, read its metadata, confirm processing status, and pull competition files for a run. When something needs to change — a new dataset version, a competition submission — Luumen shows the plan first and waits for your approval. Authentication uses an API key.
35 tools: 25 read, 10 write. Reads answer instantly. Writes require approval by default. Everything is logged.
What a governed Kaggle 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 — submit competition entry, initialize kaggle configuration, reset kaggle configuration, set kaggle configuration, 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 Kaggle — 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.