train_launch · ML Lab MCP: Risk & Policy

WHAT IT DOES

What train_launch does on ML Lab MCP

AI agents invoke train_launch 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_launch needs a policy

This tool executes training operations on potentially remote compute resources, which is a computational execution action with side effects that depend on the training configuration and dataset arguments. While it may incur financial costs, the primary action is code/process execution.

From the tool's definition Tool name 'train_launch' and description 'Launch a training run' indicate execution of training jobs across multiple backends (local GPU, Mistral, Together AI, OpenAI, Lambda Labs, RunPod, SSH-accessible VPS).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

train_launch Rate-limited

train_launch 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_launch": {
      "limits": [
        {
          "counter": "train_launch_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_launch

What does the train_launch tool do? +

Launch a training run (optionally using Codex for script generation). 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_launch? +

Register the ML Lab MCP server in PolicyLayer and add a rule for train_launch: 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_launch? +

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

Can I rate-limit train_launch? +

Yes. Add a rate_limit block to the train_launch 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_launch completely? +

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

train_launch 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.