codex_generate_training_script · ML Lab MCP: Risk & Policy

WHAT IT DOES

What codex_generate_training_script does on ML Lab MCP

AI agents invoke codex_generate_training_script 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 codex_generate_training_script needs a policy

Generating a training script is more than a write operation because the artifact produced is executable code intended to be run on potentially costly infrastructure (GPU/cloud). Misuse could produce malicious or runaway training scripts that consume significant compute resources or exfiltrate model weights.

From the tool's definition 'generate a training script' and 'from experiment config' — this tool produces executable code/scripts for ML model training, which will be run against GPU backends and cloud providers

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

codex_generate_training_script Rate-limited

codex_generate_training_script 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": {
    "codex_generate_training_script": {
      "limits": [
        {
          "counter": "codex_generate_training_script_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 codex_generate_training_script

What does the codex_generate_training_script tool do? +

Have Codex generate a training script from experiment config. 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 codex_generate_training_script? +

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

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

Can I rate-limit codex_generate_training_script? +

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

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

codex_generate_training_script 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.