LILT MCP
for LuumenAI
Check translation jobs, read credit balances, and start verified work with approval
Connect LILT and your team can ask about localization work in plain language. Check where a translation job stands, list jobs and trained models, pull a download link for finished work, and read remaining credit balances. When something needs to change — a verified translation job, a file upload, a new trained model — the agent shows the plan first and waits for your approval. Luumen connects through OAuth with dynamic client registration.
The LILT MCP toolbox
9 tools: 6 read, 3 write. Reads answer instantly. Writes require approval by default. Everything is logged.
- ReadCheck job statusChecks the status of a verified translation job.
- ReadDownload jobTriggers a job export and returns a download link for the completed job.
- ReadGet credit balance informationRetrieves all available credit balances for the authenticated user.
- ReadHello worldReturns a friendly hello world message.
- ReadList resourcesLists and filters jobs or models.
- ReadTranslate textTranslates text using LILT's instant translate API.
- WriteCreate trained modelCreates a new trained translation model for a specific language pair. Approval by default
- WriteTranslate files with verificationCreate a verified translation job that will be assigned to professional LILT linguists for translation and review. Approval by default
- WriteUpload fileUpload a file to LILT for translation. Approval by default
One prompt, start to finish
What a governed LILT MCP run looks like inside Luumen.
Questions
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 — create trained model, translate files with verification, upload file — 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 LILT 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.
Often connected alongside
All integrations
Adobe Marketing Agent MCPAdobe Experience Platform context, sandbox switches, and async task status
AffindaRead parsed documents, collections, and annotations — change them with approval
Agent MailGive the agent its own mailbox for reading threads and sending updates
AI/ML APIInspect assistants, threads, and runs — and change them as approved stepsPut LILT MCP to work with Luumen
Connect in minutes. Every action scoped, approved, and audited from day one.