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. Includes 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. 13 tools covering the full workflow: check_logic — FREE. Mathematically prove reasoning is consistent before acting on it. make_rules — write guardrails in plain English, ICME compiles them to formal logic via Automated Reasoning. check_action / quick_check — verify any agent action against your policy. SAT = allowed, UNSAT = blocked. verify_proof — independently verify the ZK receipt from any prior check. get_scenarios / run_tests — test your policy with AWS Automated Reasoning scenarios before deploying. Account & billing — create account ($5 USDC or card), top up credits, pay per call via x402. Docs: https://docs.icme.io

MCP readiness

B · 84/100

Readiness is how fully this listing follows its protocol and how it behaved in our probes over 30 days. It is shown for reference and does not move it in search. Search order and leaderboards use the separate quality grade (here B, 78.8/100), which weighs availability, conformance, p95 speed and descriptor. How the two differ

Valid MCP handshake	10/10	initialize and tools/list both answered.
Live MCP endpoint	25/25	Endpoint answers the MCP initialize handshake (1426 ms).
Protocol revision	5/10	Speaks MCP 2025-03-26, 3 revision(s) behind 2026-07-28.
Signed descriptor	n/a	No MCP standard defines a signed server descriptor.
Uptime (30 days)	15/15	31/31 probes succeeded over 30 days (100%).
Tool declaration	10/10	Lists 14 tool(s) with descriptions.
Verified identity	5/10	Publisher declared (repository, package or homepage); claim this listing to verify domain control.
Freshness + modern flags	4/5	seen in a source within 7 days.
Auth declaration	2/5	Declares credential scheme: smithery_api_key.

Applicable criteria total 90 points, scaled to 100.

Responsiveness: Responsive (1426 ms; bands ≤2.5 s, ≤5 s, ≤8 s, slower; penalty only).

Measured 2026-11-11.

Nine criteria, the same as the A2A readiness score, read from our daily MCP probe (initialize + tools/list) and 30-day probe history. No MCP standard defines a signed server descriptor, so that criterion is n/a and the other 90 points are scaled to 100. Grades: A>=90, B>=75, C>=60, D>=40, F<40. Display only: search order uses the quality grade.

Compared with peers

Against 53,039 reachable MCP servers in our daily snapshot (2026-11-12 06:46 UTC). Display only; it does not change search order.

Readiness: Higher than 75% of peers; This listing 84 · peer median 81
Latency: Faster than 37% of peers; This listing 439 ms · peer median 326 ms

Where it loses the most points, and how to win them back

Protocol revision −5 — Support the current protocol revision.
Now: Speaks MCP 2025-03-26, 3 revision(s) behind 2026-07-28.
Verified identity −5 — Claim the listing and prove control of its domain.
Now: Publisher declared (repository, package or homepage); claim this listing to verify domain control.
Auth declaration −3 — State how to authenticate (an auth scheme, or that none is needed).
Now: Declares credential scheme: smithery_api_key.

How many agent tools actually work · All statistics

Listed in

Directories this entry was found in.

smithery since 2026-06-04 ↗

How to connect

MCP endpoint (streamable-http)

https://server.smithery.ai/icme-labs/preflight/mcp

JSON-RPC initialize probe

curl -X POST https://server.smithery.ai/icme-labs/preflight/mcp \
  -H 'Content-Type: application/json' \
  -H 'Accept: application/json, text/event-stream' \
  -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{}}'

Homepage

https://docs.icme.io/

Listed at (smithery)

https://docs.icme.io/