Search scholarly metadata and keep private OpenAlex collections current
OpenAlex holds metadata on works, authors, institutions, sources, topics, funders, and awards. Luumen reads it on request: resolve an ambiguous name, pull a work record, group results by year or venue, or check your API key budget before a large query. Changes to your private collections are previewed first, then applied on approval.
14 tools: 9 read, 5 write. Reads answer instantly. Writes require approval by default. Everything is logged.
What a governed OpenAlex 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 — add collection entities, create collection, delete collection, remove collection entities, and more — is shown as a plan and requires approval by default, including the 2 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 OpenAlex — 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.