trace_record · Threadwork MCP: Risk & Policy

WHAT IT DOES

What trace_record does on Threadwork

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

WHY IT NEEDS A POLICY

Why trace_record needs a policy

The tool records (writes) trace events to persistent storage, which is a reversible data creation operation. This is Write category rather than Read (it creates data, not retrieves it) or Destructive (recording traces is not irreversible deletion).

From the tool's definition Tool description states 'Record a step-level trace event' and mentions 'persistent storage', indicating it creates/writes trace data to storage.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

trace_record Rate-limited

trace_record 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": {
    "trace_record": {
      "limits": [
        {
          "counter": "trace_record_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 Threadwork, so you can run agents against it safely.

FAQ

Questions about trace_record

What does the trace_record tool do? +

Record a step-level trace event for a Threadwork task. Spike-grade; persistent storage moves to packages/mcp-server in W7. It is categorised as a Write tool in the Threadwork MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on trace_record? +

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

What risk level is trace_record? +

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

Can I rate-limit trace_record? +

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

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

trace_record is provided by the Threadwork MCP server (tianqbu/threadwork). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.