requeue_dead_task · State Trace MCP: Risk & Policy

WHAT IT DOES

What requeue_dead_task does on State Trace

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

WHY IT NEEDS A POLICY

Why requeue_dead_task needs a policy

This tool modifies task state by moving it from the dead-letter queue back to the active queue and resetting its attempt count. This is a reversible write operation — it changes queue state but does not delete data or execute code. Misuse could cause unintended retries of failed tasks, hence medium severity.

From the tool's definition Move a task out of the dead-letter queue back to the queue. Emits task.requeued_from_dlq. Resets attemptCount by default.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

requeue_dead_task Rate-limited

requeue_dead_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": {
    "requeue_dead_task": {
      "limits": [
        {
          "counter": "requeue_dead_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 State Trace, so you can run agents against it safely.

FAQ

Questions about requeue_dead_task

What does the requeue_dead_task tool do? +

Move a task out of the dead-letter queue back to the queue. Emits task.requeued_from_dlq. Resets attemptCount by default. It is categorised as a Write tool in the State Trace MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on requeue_dead_task? +

Register the State Trace MCP server in PolicyLayer and add a rule for requeue_dead_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 State Trace. Nothing to install.

What risk level is requeue_dead_task? +

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

Can I rate-limit requeue_dead_task? +

Yes. Add a rate_limit block to the requeue_dead_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 requeue_dead_task completely? +

Set action: deny in the PolicyLayer policy for requeue_dead_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 requeue_dead_task? +

requeue_dead_task is provided by the State Trace MCP server (agent-pattern-labs/state-trace). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.