train_stop · ML Lab MCP: Risk & Policy

WHAT IT DOES

What train_stop does on ML Lab MCP

AI agents invoke train_stop to trigger actions in ML Lab 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 train_stop needs a policy

This tool executes a command to halt a training process, which is an external operation whose effects depend on which training run is targeted (via arguments). While stopping a process is technically reversible (the run can be restarted), it is not a Read operation (no data retrieval), not a Write operation (does not create/modify persistent data), and not Destructive in the traditional sense (training artifacts…

From the tool's definition Tool name 'train_stop' performs an operational action that interrupts an active process. Description states 'Stop a training run' — an active intervention that triggers external effects on a running machine learning backend system.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

train_stop Rate-limited

train_stop 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": {
    "train_stop": {
      "limits": [
        {
          "counter": "train_stop_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 ML Lab MCP, so you can run agents against it safely.

FAQ

Questions about train_stop

What does the train_stop tool do? +

Stop a training run. It is categorised as a Execute tool in the ML Lab 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 train_stop? +

Register the ML Lab MCP server in PolicyLayer and add a rule for train_stop: 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 ML Lab MCP. Nothing to install.

What risk level is train_stop? +

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

Can I rate-limit train_stop? +

Yes. Add a rate_limit block to the train_stop 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 train_stop completely? +

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

train_stop is provided by the ML Lab MCP server (pushpullcommitpush/ml-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.