// SCAN REPORT

Mcp Todo

9 tools. 6 can modify or destroy data without limits.

2 destructive tools with no built-in limits. Policy required.

Last updated: 29 Jun 2026

6 can modify or destroy data

3 read-only

9 tools total

Community server · catalogue entry verified 29/06/2026

How to control Mcp Todo ↓

TOOL MAP

What Mcp Todo exposes to your agents

Read (3) Write / Execute (4) Destructive / Financial (2)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Mcp Todo tools

Destructive · High delete_memo The delete_memo tool permanently removes memo data with no undo capability. Destructive · High delete_todo This tool permanently removes todos from the system without possibility of recovery. Write · Low create_memo This tool creates or adds a new memo to the system, which is reversible data creation (can be updated or deleted later). Write · Medium create_todo This tool creates new todo items, which is a reversible write operation.

6 of Mcp Todo's 9 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 Todo

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

Deny destructive operations

{
  "delete_memo": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "create_memo": {
    "limits": [
      {
        "counter": "create_memo_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_memo": {
    "limits": [
      {
        "counter": "get_memo_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 Todo — 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 TODO →

Instant setup, no code required.

FULL CATALOGUE

All 9 Mcp Todo tools

DESTRUCTIVE 2 tools

Destructive delete_memo 메모를 삭제합니다. Destructive delete_todo 일정을 삭제합니다.

WRITE 4 tools

Write create_memo 새로운 메모를 생성합니다. Write create_todo 새로운 일정을 생성합니다. Write update_memo 기존 메모를 수정합니다. Write update_todo 기존 일정을 수정합니다.

READ 3 tools

Read get_memo 특정 메모의 상세 내용을 조회합니다. Read list_memos 메모 목록을 조회합니다. 최근 수정순으로 정렬됩니다. Read list_todos 일정 목록을 조회합니다. 카테고리나 날짜로 필터링할 수 있습니다.

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Mcp Todo

Can an AI agent delete data through the Mcp Todo MCP server? +

Yes. The Mcp Todo server exposes 2 destructive tools including delete_memo, delete_todo. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Mcp Todo? +

The Mcp Todo server has 4 write tools including create_memo, create_todo, update_memo. 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 Todo.

How many tools does the Mcp Todo MCP server expose? +

9 tools across 3 categories: Destructive, Read, Write. 3 are read-only. 6 can modify, create, or delete data.

How do I enforce a policy on Mcp Todo? +

Register the Mcp Todo 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 Todo tool call.

Deterministic rules across all 9 Mcp Todo tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MCP TODO →

Instant setup, no code required.

9 Mcp Todo tools catalogued and risk-classified — across an index of 43,000+ MCP servers.