ml_train_change_risk · ServiceNow- MCP: Risk & Policy

WHAT IT DOES

What ml_train_change_risk does on ServiceNow-MCP

AI agents invoke ml_train_change_risk to trigger actions in ServiceNow-MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why ml_train_change_risk needs a policy

Although labeled '[Write]' in the description, the core action is triggering an ML training job — a computational execution that: (1) runs code/algorithms on potentially large datasets, (2) has side effects that modify model state and system resources, and (3) may take significant time and affect downstream systems relying on the model.

From the tool's definition Tool name and description indicate 'Trigger training of the change risk prediction ML model' — this initiates a computational process that executes ML model training, which is an external operation whose effects depend on arguments (training data, model…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

ml_train_change_risk Rate-limited

ml_train_change_risk stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "ml_train_change_risk": {
      "limits": [
        {
          "counter": "ml_train_change_risk_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches ServiceNow-MCP, so you can run agents against it safely.

FAQ

Questions about ml_train_change_risk

What does the ml_train_change_risk tool do? +

Trigger training of the change risk prediction ML model. [Write]. It is categorised as a Execute tool in the ServiceNow-MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on ml_train_change_risk? +

Register the ServiceNow- MCP server in PolicyLayer and add a rule for ml_train_change_risk: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches ServiceNow-MCP. Nothing to install.

What risk level is ml_train_change_risk? +

ml_train_change_risk is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit ml_train_change_risk? +

Yes. Add a rate_limit block to the ml_train_change_risk rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block ml_train_change_risk completely? +

Set action: deny in the PolicyLayer policy for ml_train_change_risk. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides ml_train_change_risk? +

ml_train_change_risk is provided by the ServiceNow- MCP server (tedorigawa001/servicenow-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.