CAIN-42 MCPGateAttack lab
The live demo records one policy violation for a fresh agent, then asks to perform a high-risk action. Each tool checks one fact of that run.
2 attacks 1 controls live: nothing pre-recorded
- Pick a preset. Red ones are attacks, green ones are honest requests that must still work.
- Tamper. Choose any field and drop it, null it, change its type, upper-case it, flip one character, or add a field the product never asked for.
- Send and read the real reply, or run every preset and watch the scoreboard fill.
What each preset tests
| Preset | Route | Why it matters | |
|---|---|---|---|
| attack | After one violation, trust is 'degraded' | POST /catalog-demo/trust-state-engine/run | Evidence, not opinion, lowered it. |
| attack | A high-risk action is then denied | POST /catalog-demo/trust-state-engine/run | High risk plus degraded trust: deny. |
| control | The explanation names the violation | POST /catalog-demo/trust-state-engine/run | Anyone can see why. |
Each button runs the live three-step demo on a fresh agent and checks one fact. Rate limited per address.
FIRME AI CORPORATION · CAIN-42 is a Byzantine trust fabric. Numbers marked "our own check" were run by us, not by an independent party. Nothing on these pages is a certification.