break_down_task

A write tool on the Coach AI MCP server.

SERVERCoach AI SOURCE94aharris/coach-ai

Medium RISK CLASS

Category Write

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/94aharris-coach-ai/break-down-task.md

WHAT IT DOES

What break_down_task does on Coach AI

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

RISK

Why break_down_task is rated Medium

The tool appears to create or modify task data (reversible Write operation) rather than delete (Destructive), execute arbitrary code (Execute), or trigger external operations. Without a description, confidence is reduced, but context from related Write tools (add_todo, add_task_context) and the task management domain strongly suggest data creation/modification.

From the tool's definition Tool name is 'break_down_task' with no description provided. Based on sibling tools like 'add_todo', 'add_task_context', and 'batch_assign_timeframes', this server is a task management system.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs break_down_task safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Coach AI, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For break_down_task, this is the rule to start with:

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.

The button opens the PolicyLayer dashboard: create your workspace, connect Coach AI, apply this rule, and every break_down_task call is checked against it from then on.

FAQ

Questions about break_down_task

What does the break_down_task tool do? +

break_down_task is a write tool on the Coach AI MCP server. It is categorised as a Write tool in the Coach AI 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 Coach AI 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 Coach AI. 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 Coach AI MCP server (94aharris/coach-ai). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Coach AI, and thousands of servers like it.

This server

All 28 Coach AI tools →

Across the catalogue

create_task on 0rca Dojo MCP Server →create-task on Kanban MCP Server → The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →