todo_write · MCP Claude Code MCP: Risk & Policy

WHAT IT DOES

What todo_write does on MCP Claude Code

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

WHY IT NEEDS A POLICY

Why todo_write needs a policy

The name 'todo_write' most naturally denotes creating or modifying TODO entries or files, which is a Write operation (reversible data modification). While the empty description prevents certainty, the server's documented ability to 'modify files' and the pattern of sibling write-oriented tools (edit, content_replace, multi_edit) support this classification.

From the tool's definition Tool name 'todo_write' implies creating or modifying a TODO list/file. Server context describes 'modify files' and 'direct file system interactions', and sibling tools include 'edit' and 'multi_edit', which are Write operations.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

todo_write Rate-limited

todo_write 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": {
    "todo_write": {
      "limits": [
        {
          "counter": "todo_write_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 Claude Code, so you can run agents against it safely.

FAQ

Questions about todo_write

What does the todo_write tool do? +

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

How do I enforce a policy on todo_write? +

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

What risk level is todo_write? +

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

Can I rate-limit todo_write? +

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

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

todo_write is provided by the MCP Claude Code MCP server (sdglbl/mcp-claude-code). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.