complete_task · State Trace MCP: Risk & Policy

WHAT IT DOES

What complete_task does on State Trace

AI agents use complete_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 complete_task needs a policy

This tool modifies the state of a task by changing its status from running to completed and may add new context snapshots. These are Write operations (state changes that can be reversed or corrected) rather than Destructive ones.

From the tool's definition Tool description states "Mark a running task as completed. Optionally append a new run context snapshot." The action of marking a task complete and appending snapshots are reversible state modifications.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

complete_task Rate-limited

complete_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": {
    "complete_task": {
      "limits": [
        {
          "counter": "complete_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 complete_task

What does the complete_task tool do? +

Mark a running task as completed. Optionally append a new run context snapshot. 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 complete_task? +

Register the State Trace MCP server in PolicyLayer and add a rule for complete_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 complete_task? +

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

Can I rate-limit complete_task? +

Yes. Add a rate_limit block to the complete_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 complete_task completely? +

Set action: deny in the PolicyLayer policy for complete_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 complete_task? +

complete_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.