ml_evaluate_model

What ml_evaluate_model does on NowAIKit — ServiceNow AI Toolkit

AI agents call ml_evaluate_model to retrieve information from NowAIKit — ServiceNow AI Toolkit without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Why ml_evaluate_model is rated Low

The tool retrieves and reports metrics and status information about an already-trained ML model. This is a read-only operation with no side effects, no code execution, no data modification, and no destructive capability. The worst-case misuse is retrieving model performance data that may be sensitive, but this is a low-severity information disclosure risk rather than a system-level threat.

From the tool's definition Tool description states 'Get accuracy, training status, and metrics' — these are retrieval operations that query existing model evaluation data without modifying or executing anything.

The rule that runs ml_evaluate_model safely

PolicyLayer is an MCP gateway: it sits between your AI agents and NowAIKit — ServiceNow AI Toolkit, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For ml_evaluate_model, this is the rule to start with:

{
  "version": "1",
  "default": "deny",
  "tools": {
    "ml_evaluate_model": {}
  }
}

Questions about ml_evaluate_model