ml_train_anomaly_detector · ServiceNow- MCP: Risk & Policy

WHAT IT DOES

What ml_train_anomaly_detector does on ServiceNow-MCP

AI agents invoke ml_train_anomaly_detector 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_anomaly_detector needs a policy

Although labeled [Write], the tool's core function is to execute (trigger/initiate) an ML training process, not merely create or modify reversible data records. ML training is computational execution with non-trivial side effects and resource consumption. This falls under Execute rather than Write.

From the tool's definition Trigger training of an anomaly detection model — this invokes a machine learning pipeline execution with side effects that depend on the specified table/field arguments.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

ml_train_anomaly_detector Rate-limited

ml_train_anomaly_detector 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_anomaly_detector": {
      "limits": [
        {
          "counter": "ml_train_anomaly_detector_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_anomaly_detector

What does the ml_train_anomaly_detector tool do? +

Trigger training of an anomaly detection model for a specific table/field. [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_anomaly_detector? +

Register the ServiceNow- MCP server in PolicyLayer and add a rule for ml_train_anomaly_detector: 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_anomaly_detector? +

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

Can I rate-limit ml_train_anomaly_detector? +

Yes. Add a rate_limit block to the ml_train_anomaly_detector 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_anomaly_detector completely? +

Set action: deny in the PolicyLayer policy for ml_train_anomaly_detector. 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_anomaly_detector? +

ml_train_anomaly_detector 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.