codex_run · ML Lab MCP: Risk & Policy

WHAT IT DOES

What codex_run does on ML Lab MCP

AI agents invoke codex_run 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_run needs a policy

This tool permits execution of arbitrary tasks on potentially remote ML infrastructure with access to GPU resources and cloud providers. An AI agent could use this to run malicious code, exfiltrate data, perform unauthorized computation, or compromise external systems.

From the tool's definition Tool description states "Run an arbitrary task with Codex (for advanced use)" — the word "arbitrary" combined with "run" indicates execution of uncontrolled code or commands.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

codex_run Rate-limited

codex_run 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_run": {
      "limits": [
        {
          "counter": "codex_run_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_run

What does the codex_run tool do? +

Run an arbitrary task with Codex (for advanced use). 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_run? +

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

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

Can I rate-limit codex_run? +

Yes. Add a rate_limit block to the codex_run 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_run completely? +

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

codex_run 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.