decompose_goal · Agent Runtime MCP: Risk & Policy

WHAT IT DOES

What decompose_goal does on Agent Runtime

AI agents use decompose_goal to create or update resources in Agent Runtime — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Agent Runtime environment.

WHY IT NEEDS A POLICY

Why decompose_goal needs a policy

This tool creates new task records (decomposed from a goal) as indicated by 'Returns task IDs that were created.' It is a Write operation since it creates data reversibly. There is no indication of code execution, deletion, or financial operations.

From the tool's definition Decompose a goal into tasks using AI. Returns task IDs that were created.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

decompose_goal Rate-limited

decompose_goal 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": {
    "decompose_goal": {
      "limits": [
        {
          "counter": "decompose_goal_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 Agent Runtime, so you can run agents against it safely.

FAQ

Questions about decompose_goal

What does the decompose_goal tool do? +

Decompose a goal into tasks using AI. Returns task IDs that were created. It is categorised as a Write tool in the Agent Runtime MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on decompose_goal? +

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

What risk level is decompose_goal? +

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

Can I rate-limit decompose_goal? +

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

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

decompose_goal is provided by the Agent Runtime MCP server (marc-shade/agent-runtime-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.