log_judgment_call · Claude Operator MCP: Risk & Policy

WHAT IT DOES

What log_judgment_call does on Claude Operator

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

WHY IT NEEDS A POLICY

Why log_judgment_call needs a policy

The tool likely creates or modifies log/judgment records in the operator's memory system (consistent with sibling tools like 'update_memory' and 'search_memory'). While a pure read would not justify Write classification, the verb 'log' typically implies recording/persistence.

From the tool's definition Tool name 'log_judgment_call' suggests recording or storing a decision/judgment; the context of a memory-managed autonomous operator implies writing to a persistent store. The description is empty, reducing certainty.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

log_judgment_call Rate-limited

log_judgment_call 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": {
    "log_judgment_call": {
      "limits": [
        {
          "counter": "log_judgment_call_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 Claude Operator, so you can run agents against it safely.

FAQ

Questions about log_judgment_call

What does the log_judgment_call tool do? +

log_judgment_call. It is categorised as a Write tool in the Claude Operator MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on log_judgment_call? +

Register the Claude Operator MCP server in PolicyLayer and add a rule for log_judgment_call: 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 Claude Operator. Nothing to install.

What risk level is log_judgment_call? +

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

Can I rate-limit log_judgment_call? +

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

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

log_judgment_call is provided by the Claude Operator MCP server (moygulati/claude-operator). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.