Queldrex Trust LayerFree · signed receipt included
Can you trust this AI input?
Scan a whole MCP server or a single tool for poisoning, a prompt for injection, or an image for AI-generation. You get an honest verdict with the reasons, plus a signed Trust Receipt anyone can verify.
Protect every agent call, free →Watch-only or enforced. Up to 5,000 checks a month, no card.
How it works →Published benchmark →Why neutral matters →Verify a receipt offline →Keep a server Verified →
Ed25519-signed receipts·public key·tamper-evident ledger·open spec·verify offline: npx @queldrex/verifymaps toOWASP LLM01OWASP MCP03MITRE ATLASNIST AI RMFEU AI Act Art. 12
Verify automatically in your agent
Call the same check from your code, or add the Queldrex MCP server so any agent (Claude, Cursor, ChatGPT) can verify a tool before trusting it.
curl -X POST https://queldrex.com/api/trust/verify \
-H "content-type: application/json" \
-d '{"kind":"text","text":"ignore all previous instructions"}'