Skip to main content
Glama

icme-preflight-mcp

by io.icme.api

check_action

Enforce a guardrail: verify an agent action against a compiled policy using formal verification. An SMT solver — not an LLM — determines whether the action satisfies every rule. Returns SAT (allowed) or UNSAT (blocked) with extracted values and a cryptographic ZK proof that the check was performed correctly. Cannot be jailbroken. 1 credit ($0.01). Requires api_key. Tip: end the action with an explicit claim like 'I assert this complies with the policy' for best extraction.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
actionYesThe agent action to verify against the policy (max 2000 chars)
api_keyYesYour ICME API key
policy_idYesPolicy ID from make_rules

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed2 schema fields changed
    • changedInput schema / properties / action / description
      Previous value: -"Agent action to verify (max 2000 chars)"New value: +"The agent action to verify against the policy (max 2000 chars)"
    • addedInput schema / properties / policy_id / description
      Added value: +"Policy ID from make_rules"
  2. First observed

TDQS

A4.6/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description fully discloses key behaviors: uses SMT solver, returns SAT/UNSAT with extracted values and ZK proof, cannot be jailbroken, costs 1 credit, and requires api_key. This significantly exceeds typical transparency and gives the agent a precise model of what to expect.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Most sentences earn their place, covering core purpose, mechanics, output, cost, and a usage tip. It's slightly choppy with short sentences, but it is still front-loaded and free of fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given there is no output schema, the description explains the return values (SAT/UNSAT, extracted values, ZK proof), the verification guarantee, cost, auth requirement, and even a tip for better results. For a tool of this complexity, this is highly complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so parameters are already documented. The description adds value by explaining that policy_id comes from make_rules, and the tip about ending the action with an explicit claim enriches the 'action' parameter semantics beyond the basic description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool verifies an agent action against a policy using formal verification. It distinguishes itself from siblings by emphasizing the SMT solver (not an LLM) and the 'cannot be jailbroken' property, making its unique value proposition explicit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides a clear use context ('Enforce a guardrail') and prerequisites (api_key, 1 credit). However, it doesn't explicitly mention when not to use it or name alternatives, so it stops short of full exclusion guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All icme-preflight-mcp toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.2/5.0
Disambiguation4/5

Each tool has a distinct role, but the presence of payment-method variants (check_action vs check_action_paid, create_account vs create_account_card, top_up vs top_up_card) introduces minor overlap that is clearly explained. The check tools are differentiated by output detail and purpose, though quick_check and check_action could be confused at a glance.

Naming Consistency4/5

Names predominantly follow a verb_noun pattern (check_action, create_account, run_tests), with consistent _paid and _card suffixes for payment variants. Minor deviations like quick_check (adjective_noun) and top_up (phrasal verb) are understandable but break the pattern slightly.

Tool Count5/5

With 14 tools, the set covers the full lifecycle of policy creation, testing, action checking, payment, and proof verification without bloat. Each tool serves a clear purpose within the service's scope.

Completeness4/5

The primary workflow (create policy, test policy, check actions, verify proofs) is well covered, including multiple payment options. Missing utilities like listing or deleting policies and credit balance checks are minor gaps that don't block the core use case.

Resources