# SignalHarness Agent Permission Policy Check

> SignalHarness Agent Permission Policy Check is a paid API for AI agents from signalharness.ai, paid per call via x402, $0.01/call, status unknown (last checked 2026-09-15).

Evaluates a JSON request payload against agent permission policies and returns an analysis of compliance, warnings, and evidence scope.

## Facts

- Endpoint: POST https://signalharness.ai/api/agent/services/agent_permission_policy_check/invoke
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/signalharness-agent-permission-policy-check-e5925ea8
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_YdSaFbOj4Sgy-4kMIr_vk

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 signalharness-agent-permission-policy-check-e5925ea8 -d '<json body>'
```

Example prompt: Check whether this agent request JSON is allowed under the permission policy: {"action":"send_email","recipient":"external_user@example.com","agentId":"agent-42"} — I need to know if there are any warnings or violations before proceeding.

## When to prefer this

Choose this endpoint when an AI agent needs to validate a specific action or request payload against a permission policy before executing it, particularly in multi-agent pipelines where governance and compliance checks are required. It is ideal for pre-flight checks in autonomous agent workflows, audit trails, and safety guardrails. Prefer this over generic JSON validators when you need policy-aware analysis with agent-native context and a cryptographic receipt.

## Known failure modes

- Malformed or invalid JSON in request_json field causes validation failure
- request_json exceeds 65536 character limit — rejected with input size error
- Payment not received — endpoint returns HTTP 402 requiring USDC payment on Base
- Caller-supplied data that is syntactically valid but semantically ambiguous may return generic warnings rather than precise policy violations
- Network or service unavailability returns a non-200 status with no result

## How this service works

Explore 330 pay-per-call x402 API services and 27 agent-native digital products, with Base USDC pricing, secure Polar checkout, and free discovery.

## Output

Returns a structured result containing: the analysis as a JSON string, a list of policy warnings (e.g. 'Verify the caller-supplied data before relying on this result.'), the evidence scope (e.g. 'caller_supplied_data'), the service ID, a status ('succeeded' or otherwise), and a receipt with payment details, execution metadata, and a SHA-256 result hash for integrity verification.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "request_json": {
   "type": "string",
   "maxLength": 65536,
   "minLength": 2
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "replay": false,
  "result": {
   "warnings": [
    "Verify the caller-supplied data before relying on this result."
   ],
   "service_id": "agent_permission_policy_check",
   "analysis_json": "{\"example\":\"schema-valid caller-supplied data\"}",
   "evidence_scope": "caller_supplied_data"
  },
  "status": "succeeded",
  "receipt": {
   "asset": "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913",
   "usage": [],
   "status": "succeeded",
   "network": "eip155:8453",
   "artifacts": [],
   "endedAtMs": 0,
   "latencyMs": 0,
   "paymentId": "example-payment",
   "receiptId": "example-receipt",
   "requestId": "example-request",
   "serviceId": "agent_permission_policy_check",
   "executionId": "example-execution",
   "startedAtMs": 0,
   "amountAtomic": "10000",
   "resultSha256": "a9fe2163170bb318573d3bf21557e4dd8c8065a71c070cfdb554ef15cd48ce6c",
   "serviceVersion": "1.0.0",
   "settlementReference": "0x0000000000000000000000000000000000000000000000000000000000000000"
  },
  "artifacts": [],
  "requestId": "example-request",
  "executionId": "example-execution"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/signalharness-agent-permission-policy-check-e5925ea8/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from signalharness.ai](https://www.zero.xyz/host/signalharness.ai/llms.txt)