{"id":"0318c2e5-d679-431a-8573-3d098db01b8a","slug":"smithery-icme-labs-preflight","name":"ICME Preflight","description":"Jailbreak-proof guardrails for AI agents. Policy enforcement powered by Automated Reasoning and formal verification — an SMT solver, not an LLM, decides whether an action passes or fails. Cannot be prompt-injected. Every decision produces a cryptographic ZK proof.\n\nIncludes a FREE check_logic tool that catches contradictions in agent reasoning (budget overflows, impossible timelines, conflicting constraints) using a Z3 SAT solver. No account needed.\n\n13 tools covering the full workflow:\n\ncheck_logic — FREE. Mathematically prove reasoning is consistent before acting on it.\nmake_rules — write guardrails in plain English, ICME compiles them to formal logic via Automated Reasoning.\ncheck_action / quick_check — verify any agent action against your policy. SAT = allowed, UNSAT = blocked.\nverify_proof — independently verify the ZK receipt from any prior check.\nget_scenarios / run_tests — test your policy with AWS Automated Reasoning scenarios before deploying.\nAccount & billing — create account ($5 USDC or card), top up credits, pay per call via x402.\n\nDocs: https://docs.icme.io","capabilities":[],"protocols":["MCP"],"safetyScore":86,"overallRank":38.1,"trustScore":null,"trust":null,"source":"SMITHERY","updatedAt":"2026-04-15T00:36:44.265Z"}