TruthScan
for LuumenAI
Check whether an image, document, or recording was generated or altered
Connect TruthScan and Luumen can check content for signs of AI generation or tampering without leaving the terminal. Submit an image, text, PDF, video, or audio file for detection, read the result once the job finishes, pull the heatmap preview, and see how many detection credits the account has left. Luumen authenticates with an API key.
The TruthScan toolbox
8 tools: 3 read, 5 write. Reads answer instantly. Writes require approval by default. Everything is logged.
- ReadCheck CreditsReturn the connected TruthScan account's remaining detection credits from the canonical image detector balance endpoint.
- ReadDownload Image AssetDownload a generated preview or heatmap for an owned TruthScan image detection job.
- ReadGet Detection ResultGet the current result of an existing image, text, PDF, video, or audio detection job, optionally waiting until it finishes.
- WriteAnalyze AudioAnalyze exactly one public audio URL or uploaded audio/media file for AI generation. Approval by default
- WriteAnalyze ImageSubmit an image URL for AI-generation detection and, by default, wait for the asynchronous result. Approval by default
- WriteAnalyze PDFSubmit a publicly reachable PDF URL for asynchronous tampering detection and, by default, wait for the result. Approval by default
- WriteAnalyze TextSubmit a text value or public web URL for AI-written-text detection. Approval by default
- WriteAnalyze VideoAnalyze exactly one public video URL or uploaded video for AI generation or face swapping. Approval by default
One prompt, start to finish
What a governed TruthScan run looks like inside Luumen.
Questions
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 — analyze audio, analyze image, analyze pdf, analyze text, and more — 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 TruthScan — 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 TruthScan to work with Luumen
Connect in minutes. Every action scoped, approved, and audited from day one.