ask_claude · Teammate MCP: Risk & Policy

WHAT IT DOES

What ask_claude does on Teammate

AI agents invoke ask_claude 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_claude needs a policy

The tool triggers an external operation (sending a question/prompt to another AI agent via an iTerm pane), which constitutes executing an action whose effects depend on the arguments passed. It is not a simple read, write, or destructive action; it initiates inter-agent communication that may cause downstream effects.

From the tool's definition 'ask_claude' — described as a 'Legacy 1:1 helper' that facilitates asking Claude questions through iTerm panes, analogous to sibling tool 'ask' which targets explicit panes

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

ask_claude Rate-limited

ask_claude 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_claude": {
      "limits": [
        {
          "counter": "ask_claude_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_claude

What does the ask_claude 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_claude? +

Register the Teammate MCP server in PolicyLayer and add a rule for ask_claude: 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_claude? +

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

Can I rate-limit ask_claude? +

Yes. Add a rate_limit block to the ask_claude 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_claude completely? +

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

ask_claude 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.