ask_codex · Teammate MCP: Risk & Policy

WHAT IT DOES

What ask_codex does on Teammate

AI agents invoke ask_codex to trigger actions in Teammate. 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 ask_codex needs a policy

The tool sends a question/message to another AI agent (Codex) through iTerm panes, triggering an external operation whose effects depend on the arguments passed. This is an inter-agent communication/execution action rather than a simple read or write. Confidence is moderate because the description is sparse and labeled as legacy, with little detail on side effects.

From the tool's definition Legacy 1:1 helper. Prefer `ask` with an explicit `target`.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

ask_codex Rate-limited

ask_codex 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": {
    "ask_codex": {
      "limits": [
        {
          "counter": "ask_codex_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 Teammate, so you can run agents against it safely.

FAQ

Questions about ask_codex

What does the ask_codex tool do? +

Legacy 1:1 helper. Prefer ask with an explicit target. It is categorised as a Execute tool in the Teammate MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on ask_codex? +

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

What risk level is ask_codex? +

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

Can I rate-limit ask_codex? +

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

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

ask_codex is provided by the Teammate MCP server (jonghklee/teammate-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.