// SCAN REPORT

MCP Token Tracker

5 tools. 3 can modify or destroy data without limits.

3 write tools that can modify data. Rate limits recommended.

Last updated: 3 Jul 2026

3 can modify or destroy data

2 read-only

5 tools total

Community server · catalogue entry verified 03/07/2026

How to control MCP Token Tracker ↓

TOOL MAP

What MCP Token Tracker exposes to your agents

Read (2) Write / Execute (3) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous MCP Token Tracker tools

Write · Medium submit_daily_report This tool creates new records in Google Sheets, a reversible data modification operation. Write · Medium log_session The tool writes session activity to a markdown file. Write · Low log_usage This tool writes/records token usage data for the current conversation to a database (SQLite or Cloudflare D1).

3 of MCP Token Tracker's 5 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control MCP Token Tracker

PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Token Tracker, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "log_session": {
    "limits": [
      {
        "counter": "log_session_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "echo": {
    "limits": [
      {
        "counter": "echo_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register MCP Token Tracker — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON MCP TOKEN TRACKER →

Instant setup, no code required.

FULL CATALOGUE

All 5 MCP Token Tracker tools

WRITE 3 tools

Write log_session vibe 코딩 세션의 작업 내용을 마크다운 파일로 기록합니다. 중요한 작업 완료 시 호출하세요. Write log_usage 현재 대화의 토큰 사용량을 기록합니다. 대화가 끝날 때마다 호출하세요. Write submit_daily_report 오늘(또는 지정한 날짜)의 토큰 사용량을 Google Sheets에 제출합니다. 중복 제출은 자동 차단됩니다.

READ 2 tools

Read echo 입력한 메시지를 그대로 반환합니다. Read get_my_stats 토큰 사용량 통계를 조회합니다.

FAQ

Questions about MCP Token Tracker

How do I prevent bulk modifications through MCP Token Tracker? +

The MCP Token Tracker server has 3 write tools including log_session, log_usage, submit_daily_report. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach MCP Token Tracker.

How many tools does the MCP Token Tracker MCP server expose? +

5 tools across 2 categories: Read, Write. 2 are read-only. 3 can modify, create, or delete data.

How do I enforce a policy on MCP Token Tracker? +

Register the MCP Token Tracker MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every MCP Token Tracker tool call.

Deterministic rules across all 5 MCP Token Tracker tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MCP TOKEN TRACKER →

Instant setup, no code required.

5 MCP Token Tracker tools catalogued and risk-classified — across an index of 43,000+ MCP servers.