# Maiat Protocol Token Forensics

> Maiat Protocol Token Forensics is a paid API for AI agents from app.maiat.io, paid per call via x402, $0.05/call, status unknown (last checked 2026-09-15).

Analyzes an ERC-20 token contract address for rug pull risk and suspicious patterns using ML-based forensics scoring

## Facts

- Endpoint: GET https://app.maiat.io/api/x402/token-forensics
- Price: $0.05/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/maiat-protocol-token-forensics-0eea5326
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_-3K01UWpCbEzFZ8FqG8ZS

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 maiat-protocol-token-forensics-0eea5326
```

Example prompt: Can you run a rug pull and fraud risk analysis on this ERC-20 token at address 0xAbC123...def456 on the Base chain and tell me the ML score and verdict?

## When to prefer this

Use this endpoint when an agent needs to quickly assess whether a specific ERC-20 token contract is potentially fraudulent, a rug pull, or otherwise suspicious before executing a trade or recommending it to a user. Prefer this over generic blockchain explorers when you need a structured ML-scored verdict rather than raw on-chain data.

## Known failure modes

- Invalid or non-existent token contract address returns error or null result
- Unsupported chain name returns validation error
- Token not indexed on specified chain returns empty or inconclusive analysis
- Network timeout or service unavailability returns 5xx error
- Malformed request body returns 400 bad request

## How this service works

The decentralized truth layer. Verifying the future of autonomous agents and trust.

## Output

Returns a JSON object with an mlScore (0-1 float indicating suspicion level), a verdict string (e.g. 'proceed' or 'avoid'), a human-readable analysis summary, and a rugPullRisk category (e.g. 'low', 'medium', 'high').

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "chain": {
   "type": "string",
   "description": "Chain name (default: base)"
  },
  "token": {
   "type": "string",
   "description": "ERC-20 token contract address"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "mlScore": 0.12,
  "verdict": "proceed",
  "analysis": "No suspicious patterns detected",
  "rugPullRisk": "low"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/maiat-protocol-token-forensics-0eea5326/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from app.maiat.io](https://www.zero.xyz/host/app.maiat.io/llms.txt)