wait_directive · AT MCP: Risk & Policy

WHAT IT DOES

What wait_directive does on ATMcp

AI agents invoke wait_directive to trigger actions in ATMcp. 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 wait_directive needs a policy

While 'wait' might initially suggest a passive Read operation, the description reveals this tool actively polls and waits on external directives in a distributed system context. The ability to control task/directive timing with configurable `wait_ms` parameters makes this an Execute action rather than Read, as it orchestrates and influences the flow of operations across the system.

From the tool's definition The tool 'wait_directive' performs a blocking operation with long-polling behavior ('long-polls until it reaches a terminal'). This is an execution action that triggers external operations and waits for completion.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

wait_directive Rate-limited

wait_directive 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": {
    "wait_directive": {
      "limits": [
        {
          "counter": "wait_directive_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 ATMcp, so you can run agents against it safely.

FAQ

Questions about wait_directive

What does the wait_directive tool do? +

Await a directive you sent. With wait_ms > 0, long-polls until it reaches a terminal. It is categorised as a Execute tool in the ATMcp MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on wait_directive? +

Register the AT MCP server in PolicyLayer and add a rule for wait_directive: 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 ATMcp. Nothing to install.

What risk level is wait_directive? +

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

Can I rate-limit wait_directive? +

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

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

wait_directive is provided by the AT MCP server (midcheck/atmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.