log_usage · MCP Token Tracker MCP: Risk & Policy

WHAT IT DOES

What log_usage does on MCP Token Tracker

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

WHY IT NEEDS A POLICY

Why log_usage needs a policy

This tool writes/records token usage data for the current conversation to a database (SQLite or Cloudflare D1). It creates or updates records but does not delete data, execute code, or involve financial transactions. The blast radius is low as it only logs usage statistics.

From the tool's definition '토큰 사용량을 기록합니다' (records token usage) and '대화가 끝날 때마다 호출하세요' (call at the end of each conversation)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

log_usage Rate-limited

log_usage 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_usage": {
      "limits": [
        {
          "counter": "log_usage_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 MCP Token Tracker, so you can run agents against it safely.

FAQ

Questions about log_usage

What does the log_usage tool do? +

현재 대화의 토큰 사용량을 기록합니다. 대화가 끝날 때마다 호출하세요. It is categorised as a Write tool in the MCP Token Tracker 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_usage? +

Register the MCP Token Tracker MCP server in PolicyLayer and add a rule for log_usage: 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 MCP Token Tracker. Nothing to install.

What risk level is log_usage? +

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

Can I rate-limit log_usage? +

Yes. Add a rate_limit block to the log_usage 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_usage completely? +

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

log_usage is provided by the MCP Token Tracker MCP server (kdkim2000/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.