Copyleaks for AI agents
Copyleaks detects plagiarism and AI-generated text, helping education and publishing teams check whether submitted content is original before it's accepted. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.
What agents do in Copyleaks.
Check text for plagiarism
Check a piece of writing against published sources before accepting it as original.
Detect AI-generated text
Detect whether a submission was likely written by AI before grading or publishing it.
Check remaining credit balance
Check the remaining credit balance before running a large batch of scans.
6 Copyleaks actions, graded by risk.
Every Copyleaks action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
5Look things up. Allowed by default.
- copyleaks.get_credit_balanceGet Credit Balance
- copyleaks.get_supported_metadataGet Supported Metadata
- copyleaks.get_ai_text_credit_balanceGet AI Text Credit Balance
- copyleaks.check_writingCheck Writing
- copyleaks.detect_ai_textDetect AI Text
write
1Create and change things. Allow, or ask the user first.
- copyleaks.moderate_textModerate Text
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Copyleaks in three steps.
- 01Your users connect CopyleaksThey add their Copyleaks api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “moderate Text” can wait for the user to approve.
- 03Any agent can actYour agent calls Copyleaks through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('copyleaks', { read: 'allow', write: 'ask', // moderate_text destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Copyleaks connects.
Users add their Copyleaks api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
The same Copyleaks connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →
- AUTH
- API key
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use Copyleaks from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Copyleaks and Arc0, answered.
Can I use Copyleaks with Claude, ChatGPT or Cursor?
Yes. Connect Copyleaks to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Copyleaks actions you allow.
How do users connect Copyleaks?
Users add their Copyleaks api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
Which Copyleaks actions can my agent take?
6 in total: 5 read, 1 write and 0 destructive, such as “moderate Text”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Copyleaks?
Yes. Allow read actions and deny writes in the Copyleaks policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Copyleaks too?
Yes. The same Copyleaks connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Copyleaks into your agent.
Your users connect Copyleaks once, under your brand. Your agent gets 6 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan