expert_delegate · Musubix MCP: Risk & Policy

WHAT IT DOES

What expert_delegate does on Musubix

AI agents invoke expert_delegate to trigger actions in Musubix. 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 expert_delegate needs a policy

This tool triggers external AI expert operations, routing tasks to specialized agents. The effects depend on the message content and which expert is selected, making it an Execute-category tool. Severity is high because an AI agent could misuse this to dispatch arbitrary tasks to specialized AI systems, with unpredictable downstream effects depending on what those experts can do.

From the tool's definition "Delegate a task to a specialized AI expert" and "system automatically selects the appropriate expert based on the message content"

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

expert_delegate Rate-limited

expert_delegate 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": {
    "expert_delegate": {
      "limits": [
        {
          "counter": "expert_delegate_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 Musubix, so you can run agents against it safely.

FAQ

Questions about expert_delegate

What does the expert_delegate tool do? +

Delegate a task to a specialized AI expert. The system automatically selects the appropriate expert based on the message content, or you can specify one explicitly. It is categorised as a Execute tool in the Musubix MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on expert_delegate? +

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

What risk level is expert_delegate? +

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

Can I rate-limit expert_delegate? +

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

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

expert_delegate is provided by the Musubix MCP server (@nahisaho/musubix-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.