delegate_to_subagents · MCP Goose Subagents Server MCP

WHAT IT DOES

What delegate_to_subagents does on MCP Goose Subagents Server

AI agents invoke delegate_to_subagents to trigger actions in MCP Goose Subagents Server. 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 delegate_to_subagents needs a policy

This tool triggers autonomous Goose CLI subagents to execute development tasks. Since it runs external CLI processes and autonomous agents whose effects depend on the arguments provided (code changes, file operations, system commands, etc.), it falls squarely in the Execute category.

From the tool's definition Delegate tasks to Goose CLI subagents for autonomous development

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

delegate_to_subagents Rate-limited

delegate_to_subagents 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": {
    "delegate_to_subagents": {
      "limits": [
        {
          "counter": "delegate_to_subagents_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 MCP Goose Subagents Server, so you can run agents against it safely.

FAQ

Questions about delegate_to_subagents

What does the delegate_to_subagents tool do? +

Delegate tasks to Goose CLI subagents for autonomous development. It is categorised as a Execute tool in the MCP Goose Subagents Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on delegate_to_subagents? +

Register the MCP Goose Subagents Server MCP server in PolicyLayer and add a rule for delegate_to_subagents: 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 MCP Goose Subagents Server. Nothing to install.

What risk level is delegate_to_subagents? +

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

Can I rate-limit delegate_to_subagents? +

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

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

delegate_to_subagents is provided by the MCP Goose Subagents Server MCP server (pc-style/goose-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.