Copyleaks
for LuumenAI
Check text for AI authorship, harmful content, and writing quality from the terminal
Connect Copyleaks and Luumen can check text for AI authorship, harmful-content labels, and writing quality without leaving the terminal. It reads your credit balances and the supported file types and languages on demand, so you know what a scan will cost and whether the content is eligible before you run one. Scans are previewed and approved.
The Copyleaks toolbox
6 tools: 3 read, 3 write. Reads answer instantly. Writes require approval by default. Everything is logged.
- ReadGet AI Text Credit BalanceReturn the connected account's separate AI Text Detector wallet balance.
- ReadGet Credit BalanceReturn the connected Copyleaks account's general plagiarism and authenticity scan credit balance.
- ReadGet Supported MetadataReturn one public Copyleaks capability catalog: OCR languages, AI text file types, cross-language options, plagiarism file types, or writing correction definitions.
- WriteCheck WritingReturn grammar, mechanics, structure, word-choice, and readability feedback synchronously. Approval by default
- WriteDetect AI TextClassify text as human- or AI-written synchronously. Approval by default
- WriteModerate TextDetect harmful-content labels in text synchronously. Approval by default
One prompt, start to finish
What a governed Copyleaks 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 — check writing, detect ai text, moderate text — 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 Copyleaks — 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 Copyleaks to work with Luumen
Connect in minutes. Every action scoped, approved, and audited from day one.