break_down_task · AgentCortex MCP: Risk & Policy

WHAT IT DOES

What break_down_task does on AgentCortex MCP

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

WHY IT NEEDS A POLICY

Why break_down_task needs a policy

This tool creates new subtask entries in the memory/project system by decomposing a parent task. It is a Write operation (reversible data creation) since subtasks can presumably be deleted or modified. The blast radius is medium because misuse could pollute a project's task structure with incorrect or unwanted subtasks, but it does not destroy existing data or have financial implications.

From the tool's definition 'Break down a complex task into smaller, manageable subtasks' — creates new subtask records derived from an existing task

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

break_down_task Rate-limited

break_down_task 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": {
    "break_down_task": {
      "limits": [
        {
          "counter": "break_down_task_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 AgentCortex MCP, so you can run agents against it safely.

FAQ

Questions about break_down_task

What does the break_down_task tool do? +

Break down a complex task into smaller, manageable subtasks. Helps with project planning and execution. It is categorised as a Write tool in the AgentCortex MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on break_down_task? +

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

What risk level is break_down_task? +

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

Can I rate-limit break_down_task? +

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

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

break_down_task is provided by the AgentCortex MCP server (sage-hq/agentcortex-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.