ml_anomaly_report · Maple MCP: Risk & Policy

WHAT IT DOES

What ml_anomaly_report does on Maple

AI agents invoke ml_anomaly_report to trigger actions in Maple. 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_anomaly_report needs a policy

The tool runs a computational process (embedding-based anomaly detection) rather than merely retrieving stored data. It triggers ML inference and may query external anonymized trace data. This constitutes an Execute action. Misuse could produce false anomaly signals misleading agent safety controls, giving it medium severity.

From the tool's definition "Run embedding-based anomaly detection on a trace" — actively executes an ML pipeline/computation on data, with optional external community baseline lookup

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

ml_anomaly_report Rate-limited

ml_anomaly_report 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_anomaly_report": {
      "limits": [
        {
          "counter": "ml_anomaly_report_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 Maple, so you can run agents against it safely.

FAQ

Questions about ml_anomaly_report

What does the ml_anomaly_report tool do? +

Run embedding-based anomaly detection on a trace, with optional community baseline from shared anonymized traces. It is categorised as a Execute tool in the Maple 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_anomaly_report? +

Register the Maple MCP server in PolicyLayer and add a rule for ml_anomaly_report: 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 Maple. Nothing to install.

What risk level is ml_anomaly_report? +

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

Can I rate-limit ml_anomaly_report? +

Yes. Add a rate_limit block to the ml_anomaly_report 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_anomaly_report completely? +

Set action: deny in the PolicyLayer policy for ml_anomaly_report. 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_anomaly_report? +

ml_anomaly_report is provided by the Maple MCP server (omar2001ramadan/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.