codex_exec · Codex MCP: Risk & Policy

WHAT IT DOES

What codex_exec does on Codex

AI agents invoke codex_exec to trigger actions in Codex. 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_exec needs a policy

This tool executes Codex commands as background jobs. While the job runs asynchronously (returning immediately with a job_id), the core capability is code execution via an external service. The severity is high because: (1) Codex can execute arbitrary operations depending on task arguments, (2) background execution may obscure monitoring, and (3) an AI agent could submit unintended or malicious Codex tasks.

From the tool's definition Tool name 'codex_exec' and description 'Run Codex non-interactively as a BACKGROUND job' indicate execution of arbitrary code.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

codex_exec Rate-limited

codex_exec 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_exec": {
      "limits": [
        {
          "counter": "codex_exec_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 Codex, so you can run agents against it safely.

FAQ

Questions about codex_exec

What does the codex_exec tool do? +

Run Codex non-interactively as a BACKGROUND job. Returns immediately with a job_id;. It is categorised as a Execute tool in the Codex 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_exec? +

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

What risk level is codex_exec? +

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

Can I rate-limit codex_exec? +

Yes. Add a rate_limit block to the codex_exec 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_exec completely? +

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

codex_exec is provided by the Codex MCP server (pigowenhsiao/codex-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.