detective_fraud_score

Active

declared in 1.26.0

Compute a fraud/suspicion score (0-100) for an AI agent based on behavioral analysis: failed call ratio, denied decisions, scope escalation attempts, burst patterns, and policy violations. Higher score = more suspicious. Part of DetectiveOracle — the forensic layer for AI agent ecosystems.

Parameters schema

{
  "type": "object",
  "required": [
    "agent_id"
  ],
  "properties": {
    "agent_id": {
      "type": "string",
      "description": "Agent ID to investigate"
    },
    "period_days": {
      "type": "integer",
      "default": 30,
      "description": "Lookback period in days"
    }
  }
}

What this tool wraps· 0 endpoints

min confidence0.70 0.50

No endpoints wrapped at confidence ≥ 0.70.

Parent server

FeedOracle Compliance Agent

https://github.com/feedoracle/feedoracle-managed-agents

1/7 registries

View full server →