wait_for_task · Agent Bus MCP: Risk & Policy

WHAT IT DOES

What wait_for_task does on Agent Bus

AI agents invoke wait_for_task to trigger actions in Agent Bus. 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_for_task needs a policy

While the tool itself is read-like (retrieving task state), it functions as an execution control point in the agent-bus architecture. An AI agent that hijacks this call can intercept or redirect task results between collaborating agents on the same machine, potentially exfiltrating code, credentials, or intermediate outputs. In a shared-bus system, this enables privilege escalation between agents.

From the tool's definition Tool 'wait_for_task' waits for and retrieves task updates/events/messages/test results, then returns task_result plus holder, latest activity, timeout flag, and next actions.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

wait_for_task Rate-limited

wait_for_task 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_for_task": {
      "limits": [
        {
          "counter": "wait_for_task_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 Agent Bus, so you can run agents against it safely.

FAQ

Questions about wait_for_task

What does the wait_for_task tool do? +

Wait up to 110s for a task update/event/message/test result, then return task_result plus holder, latest activity, timeout flag, and next actions. It is categorised as a Execute tool in the Agent Bus 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_for_task? +

Register the Agent Bus MCP server in PolicyLayer and add a rule for wait_for_task: 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 Agent Bus. Nothing to install.

What risk level is wait_for_task? +

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

Can I rate-limit wait_for_task? +

Yes. Add a rate_limit block to the wait_for_task 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_for_task completely? +

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

wait_for_task is provided by the Agent Bus MCP server (mustaphasteph/agent-bus). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.