create_goose_recipe · MCP Goose Subagents Server MCP

WHAT IT DOES

What create_goose_recipe does on MCP Goose Subagents Server

AI agents use create_goose_recipe to create or update resources in MCP Goose Subagents Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Goose Subagents Server environment.

WHY IT NEEDS A POLICY

Why create_goose_recipe needs a policy

This tool creates and stores new configuration objects (recipes) that will govern how autonomous agents execute tasks. While not destructive, it modifies the persistent state of the system by adding new executable recipes. Given that these recipes define behavior for autonomous agents performing development tasks, misconfiguration or malicious recipes could lead to unintended code execution or modifications.

From the tool's definition Tool creates a reusable Goose recipe, which is a persistent artifact that defines subagent behavior and execution logic. The name explicitly uses 'create' and the context shows it's part of a system that delegates tasks to autonomous developer teams.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

create_goose_recipe Rate-limited

create_goose_recipe stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "create_goose_recipe": {
      "limits": [
        {
          "counter": "create_goose_recipe_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

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 create_goose_recipe

What does the create_goose_recipe tool do? +

Create a reusable Goose recipe for specialized subagents. It is categorised as a Write tool in the MCP Goose Subagents Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on create_goose_recipe? +

Register the MCP Goose Subagents Server MCP server in PolicyLayer and add a rule for create_goose_recipe: 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 create_goose_recipe? +

create_goose_recipe is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit create_goose_recipe? +

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

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

create_goose_recipe 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.