TruthScan for AI agents
TruthScan detects AI-generated or manipulated content across text, images, audio, video, and PDFs, used by editors and platforms checking content authenticity. 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 TruthScan.
Analyze text for AI generation
Check a piece of writing for signs it was generated by AI, a read-only analysis.
Analyze an image for manipulation
Check an image for signs of AI generation or editing.
Check remaining credits
Read remaining detection credits before running a large batch of checks.
8 TruthScan actions, graded by risk.
Every TruthScan action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
8Look things up. Allowed by default.
- truthscan.get_detection_resultGet Detection Result
- truthscan.analyze_pdfAnalyze PDF
- truthscan.analyze_textAnalyze Text
- truthscan.analyze_audioAnalyze Audio
- truthscan.analyze_imageAnalyze Image
- truthscan.analyze_videoAnalyze Video
- truthscan.check_creditsCheck Credits
- truthscan.download_image_assetDownload Image Asset
write
0Create and change things. Allow, or ask the user first.
- No write actions.
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
TruthScan in three steps.
- 01Your users connect TruthScanThey add their TruthScan api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “updates” can wait for the user to approve.
- 03Any agent can actYour agent calls TruthScan through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('truthscan', { read: 'allow', write: 'ask', destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How TruthScan connects.
Users add their TruthScan 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 TruthScan 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 TruthScan from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
TruthScan and Arc0, answered.
Can I use TruthScan with Claude, ChatGPT or Cursor?
Yes. Connect TruthScan 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 TruthScan actions you allow.
How do users connect TruthScan?
Users add their TruthScan 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 TruthScan actions can my agent take?
8 in total: 8 read, 0 write and 0 destructive. Your policies decide which of them each agent may call.
Can I make my agent read-only in TruthScan?
Yes. Allow read actions and deny writes in the TruthScan policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call TruthScan too?
Yes. The same TruthScan connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug TruthScan into your agent.
Your users connect TruthScan once, under your brand. Your agent gets 8 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan