# CYRE Guardian Policy Check

> CYRE Guardian Policy Check is a paid API for AI agents from cyre.dev, paid per call via x402, $0.001/call, status unknown (last checked 2026-09-14).

Tests a proposed payment (amount, host, network, risk) against a sealed spend-policy token and returns an ok/fail verdict with pattern-based reasons

## Facts

- Endpoint: GET https://cyre.dev/api/policy/check
- Price: $0.001/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/cyre-guardian-policy-check-c24cd633
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_j1oXvA-TYxWcsQEv-yTcC

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability cyre-guardian-policy-check-c24cd633
```

Example prompt: Before you pay that x402 resource, check my sealed spend policy token to see if a 500000 atomic USDC payment to https://api.someservice.com via GET is actually allowed — run it through CYRE Guardian and tell me if it's ok and why.

## When to prefer this

Use this endpoint when an AI agent needs to enforce a pre-configured spend policy before executing any x402 payment — particularly when the policy is sealed into a token and you want pattern-based compliance checking rather than ad-hoc risk scoring. Prefer this over CYRE Guardian Lockbox Match when you don't have a pre-pay lockbox/intentHash and just need to check a proposed payment against standing spend rules. Prefer over Guardian Pay-route Oracle when the decision is policy-compliance (not counterparty risk) focused.

## Known failure modes

- Missing or invalid token parameter returns an error — token must be a valid sealed spend-policy token
- Invalid amountAtomic format (non-numeric string) may cause parse errors
- resourceUrl not matching any policy pattern returns ok:false with pattern reasons
- Network or host not covered by the policy token returns a non-ok result
- Expired or tampered policy token returns an authentication/validation failure
- Unsupported HTTP method (only GET, HEAD, DELETE allowed) returns a schema validation error

## How this service works

Guardian Policy Check — test a proposed pay (amount, host, network, risk) against a sealed spend-policy token. Returns ok + reasons. Patterns, not verdicts. Agent guide: https://cyre.dev/SKILL.md

## Output

Returns a JSON object with an 'ok' boolean indicating whether the proposed payment passes the sealed policy, plus an array of pattern-based reasons explaining which policy rules were matched or violated (amounts, hosts, networks, risk thresholds). Does not issue verdicts — returns patterns and signals for the agent to act on.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET",
      "HEAD",
      "DELETE"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "required": [
      "token"
     ],
     "properties": {
      "token": {
       "type": "string"
      },
      "resourceUrl": {
       "type": "string"
      },
      "amountAtomic": {
       "type": "string"
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/cyre-guardian-policy-check-c24cd633/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from cyre.dev](https://www.zero.xyz/host/cyre.dev/llms.txt)