fail_task · State Trace MCP: Risk & Policy

WHAT IT DOES

What fail_task does on State Trace

AI agents use fail_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 fail_task needs a policy

This tool modifies the state of a task by marking it as failed, which is a write operation that changes task status. While described as 'terminal,' the system has retry mechanisms via lease expiry, meaning the effect is not fully irreversible at the system level. However, misuse could prematurely terminate valid tasks, causing disruption to workflows.

From the tool's definition Mark a running task as failed. This is terminal; retries happen via lease expiry, not failTask.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

fail_task Rate-limited

fail_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": {
    "fail_task": {
      "limits": [
        {
          "counter": "fail_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 fail_task

What does the fail_task tool do? +

Mark a running task as failed. This is terminal; retries happen via lease expiry, not failTask. Pass clientToken to make retries idempotent. 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 fail_task? +

Register the State Trace MCP server in PolicyLayer and add a rule for fail_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 fail_task? +

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

Can I rate-limit fail_task? +

Yes. Add a rate_limit block to the fail_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 fail_task completely? +

Set action: deny in the PolicyLayer policy for fail_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 fail_task? +

fail_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.