Read Lokalise projects, keys, and translations, then make changes on approval
Connect Lokalise and your agent can see the state of localization work without you opening the web app: which projects exist, which languages are configured, which keys are missing translations, and what changed in the team audit log. When something needs fixing, it drafts the change, shows you the exact keys and strings, and waits for your approval before writing. Connects with an API key.
10 tools: 6 read, 4 write. Reads answer instantly. Writes require approval by default. Everything is logged.
What a governed Lokalise 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 — create keys, delete keys, update keys, update translation — 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 Lokalise — 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.