async · Joe MCP: Risk & Policy

WHAT IT DOES

What async does on JoeMCP

AI agents invoke async to trigger actions in JoeMCP. 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 async needs a policy

This tool triggers execution of arbitrary multi-step workflows via an agent system. Since it can orchestrate multiple tools including Write, Destructive, and Financial operations on a construction management platform (clients, proposals, estimates, financial data), its blast radius is critical — a misused async workflow could chain together many high-severity actions irreversibly.

From the tool's definition "Delegate complex multi-step workflows to the async-agent system", "tasks that require multiple coordinated steps", "complex orchestration"

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

async Rate-limited

async 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": {
    "async": {
      "limits": [
        {
          "counter": "async_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 JoeMCP, so you can run agents against it safely.

FAQ

Questions about async

What does the async tool do? +

Delegate complex multi-step workflows to the async-agent system with real-time progress updates. Use this for tasks that require multiple coordinated steps, data gathering from multiple sources, or complex orchestration. It is categorised as a Execute tool in the JoeMCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on async? +

Register the Joe MCP server in PolicyLayer and add a rule for async: 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 JoeMCP. Nothing to install.

What risk level is async? +

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

Can I rate-limit async? +

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

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

async is provided by the Joe MCP server (lumberjack-so/joemcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.