Official CAIN-42 IHVRK (Independent Human Verification Resource Kit): MCPGate Guard Stack
Don't trust CAIN-42. Verify CAIN-42.

What the product is said to do:
  The MCPGate Guard Stack puts several guards in front of every tool an AI agent calls (skill scope, memory firewall, delegation checks, supply-chain checks and a kill-switch for bulk exports). Ordinary work goes through; each attack is stopped by a different guard, and refused calls never reach the tool.

This kit holds 6 claim(s) from https://cainstudio.online/guide-guard-stack.html, each as the exact request and the value its answer
must contain. They were run live on 2026-11-03T22:51:48+00:00 and every answer matched (a run that does not match publishes no kit).

Check it yourself (Python 3.8+, standard library only, no CAIN-42 code, no account):
  python3 verify.py             offline: hashes, Ed25519 signature, recorded answers vs. claims
  python3 verify.py --live      also send every request again from YOUR machine and check the answers now

Compare the key fingerprint verify.py prints with https://cainstudio.online/evidence-kit-key.json,
https://mcpgate.online/evidence-kit-key.json and https://clawx.click/evidence-kit-key.json.

Scope: these claims show what the live demo does with these inputs. They are not a third-party audit, a
certification or a guarantee for inputs not listed. See the product's limits page for what it does not do.
Files: README.txt, verify.py, claims.json, transcript.json, kit-key.json, MANIFEST.json, MANIFEST.sig
