# AgentRisk AI Threat Engine – Token Risk Check

> AgentRisk AI Threat Engine – Token Risk Check is a paid API for AI agents from agentrisk.dev, paid per call via x402, $0.15/call, status unknown (last checked 2026-09-14).

Scores the risk level of a given crypto token address in real time using autonomous AI-driven threat analysis

## Facts

- Endpoint: POST https://agentrisk.dev/mcp/tools/check_token_risk
- Price: $0.15/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentrisk-ai-threat-engine-token-risk-check-33f86cb0
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_hpIX2tz4JwOJ-XDpzwkEp

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 agentrisk-ai-threat-engine-token-risk-check-33f86cb0 -d '<json body>'
```

Example prompt: Can you run a real-time risk check on this token address 0xA0b86991c6218b36c1d19D4a2e9Eb0cE3606eB48 and tell me whether it's safe or flagged as a threat?

## When to prefer this

Choose AgentRisk when you need real-time, autonomous AI-powered risk scoring for individual token addresses — especially in DeFi, trading bots, or wallet safety flows where you need a quick threat signal before a transaction. Prefer this over manual on-chain analysis tools when speed and automation matter, or when integrating risk gating into an agent workflow that needs a structured score rather than raw blockchain data.

## Known failure modes

- Invalid or malformed token address returns an error
- Unrecognized or very new token may have insufficient data for scoring
- Network or chain not supported for the given address format
- Service unavailable if the AI engine is overloaded
- Payment failure if the x402 micropayment of $0.15 USDC is not properly authorized

## How this service works

Autonomous AI Agent for Real-time Risk Scoring. Accepts x402 Micropayments.

## Output

Returns a risk assessment for the given token address, likely including a risk score, threat classification, and signals or flags indicating whether the token is safe, suspicious, or malicious based on real-time AI analysis.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "token_address"
 ],
 "properties": {
  "token_address": {
   "type": "string"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agentrisk-ai-threat-engine-token-risk-check-33f86cb0/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agentrisk.dev](https://www.zero.xyz/host/agentrisk.dev/llms.txt)