# ActionGate Risk Score API

> ActionGate Risk Score API is a paid API for AI agents from api.actiongate.xyz, paid per call via x402, $0.02/call, status unknown (last checked 2026-09-15).

Scores the risk of a proposed autonomous agent action before execution, enabling pre-execution policy gating

## Facts

- Endpoint: POST https://api.actiongate.xyz/v1/risk-score
- Price: $0.02/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/api-actiongate-xyz-65cb8924
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_xKTsAiEr5Pick0cove0Pe

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 api-actiongate-xyz-65cb8924 -d '<json body>'
```

Example prompt: Before my AI agent executes this action — transferring 500 USDC to wallet 0xABC... — run a risk score on it and tell me whether it passes the policy gate or should be blocked.

## When to prefer this

Use this endpoint when you need a fast, paid, per-call risk score specifically for autonomous agent pre-execution decisions — particularly when you need a policy gate that can block or allow actions before they are committed. Prefer this over internal heuristics when compliance, auditability, or safety guarantees are required for agentic workflows.

## Known failure modes

- Invalid or malformed action payload returns 400 error
- Insufficient USDC balance for $0.02 per-call fee results in payment failure
- Unknown action type or unsupported schema returns validation error
- Timeout if action context is too large or complex
- Service unavailable returns 503

## How this service works

Score action risk before execution.

## Output

Returns a numeric risk score and a policy gate decision (allow/block) for the proposed agent action, enabling the agent to decide whether to proceed or halt execution.

## Example request

```json
{
 "input": {
  "body": {
   "actor": {
    "actor_id": "test-agent-001"
   },
   "action": {
    "action_type": "read_data"
   },
   "request_id": "req-qa-test-001"
  },
  "type": "http",
  "bodyType": "json"
 }
}
```

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "actor": {
   "type": "object",
   "required": [
    "actor_id"
   ],
   "properties": {
    "actor_id": {
     "type": "string"
    },
    "wallet_address": {
     "type": "string"
    }
   },
   "additionalProperties": true
  },
  "action": {
   "type": "object",
   "required": [
    "action_type"
   ],
   "properties": {
    "amount": {
     "type": "string"
    },
    "target": {
     "type": "string"
    },
    "network": {
     "type": "string"
    },
    "action_type": {
     "type": "string"
    },
    "asset_symbol": {
     "type": "string"
    }
   },
   "additionalProperties": true
  },
  "context": {
   "type": "object",
   "additionalProperties": true
  },
  "request_id": {
   "type": "string"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/api-actiongate-xyz-65cb8924/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.actiongate.xyz](https://www.zero.xyz/host/api.actiongate.xyz/llms.txt)