mark_task_agent_ready · Quarterback MCP: Risk & Policy

WHAT IT DOES

What mark_task_agent_ready does on Quarterback

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

WHY IT NEEDS A POLICY

Why mark_task_agent_ready needs a policy

This tool modifies the state of a task by flagging it as ready for autonomous agent execution. It is a reversible state change (Write category), but carries medium severity because incorrectly marking tasks could trigger unintended autonomous agent actions downstream.

From the tool's definition Mark a task for autonomous agent execution

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

mark_task_agent_ready Rate-limited

mark_task_agent_ready 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": {
    "mark_task_agent_ready": {
      "limits": [
        {
          "counter": "mark_task_agent_ready_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 Quarterback, so you can run agents against it safely.

FAQ

Questions about mark_task_agent_ready

What does the mark_task_agent_ready tool do? +

Mark a task for autonomous agent execution. It is categorised as a Write tool in the Quarterback MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on mark_task_agent_ready? +

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

What risk level is mark_task_agent_ready? +

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

Can I rate-limit mark_task_agent_ready? +

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

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

mark_task_agent_ready is provided by the Quarterback MCP server (bobbyrgoldsmith/quarterback). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.