mark_task_running · State Trace MCP: Risk & Policy

WHAT IT DOES

What mark_task_running does on State Trace

AI agents use mark_task_running 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 mark_task_running needs a policy

This tool updates task state within a workflow management system. It creates or modifies data (task state transitions) but does not execute external operations, delete data irreversibly, or access financial systems. The operation is reversible — a running task can be paused, cancelled, or re-enqueued.

From the tool's definition Tool description explicitly states 'Transition a leased task into the running state' — a state change operation that modifies task metadata reversibly (tasks can be transitioned to other states or run again).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

mark_task_running Rate-limited

mark_task_running 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_running": {
      "limits": [
        {
          "counter": "mark_task_running_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 mark_task_running

What does the mark_task_running tool do? +

Transition a leased task into the running state. 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 mark_task_running? +

Register the State Trace MCP server in PolicyLayer and add a rule for mark_task_running: 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 mark_task_running? +

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

Can I rate-limit mark_task_running? +

Yes. Add a rate_limit block to the mark_task_running 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_running completely? +

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

mark_task_running 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.