mark_todo_done · Decision Tree MCP Server MCP: Risk & Policy

WHAT IT DOES

What mark_todo_done does on Decision Tree MCP Server

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

WHY IT NEEDS A POLICY

Why mark_todo_done needs a policy

The tool reversibly updates a todo item's completion status. This is a Write operation because it modifies data without irreversibly deleting it or executing arbitrary code. The severity is low because the blast radius of a misuse is confined to marking incorrect todos as done in a personal to-do list, with no financial, destructive, or system-level consequences.

From the tool's definition Tool description states 'Mark a todo item as completed by ID' — this modifies the state of an existing todo item from incomplete to completed, updating stored data in Redis.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

mark_todo_done Rate-limited

mark_todo_done 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": {
    "mark_todo_done": {
      "limits": [
        {
          "counter": "mark_todo_done_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 Decision Tree MCP Server, so you can run agents against it safely.

FAQ

Questions about mark_todo_done

What does the mark_todo_done tool do? +

Mark a todo item as completed by ID. It is categorised as a Write tool in the Decision Tree MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on mark_todo_done? +

Register the Decision Tree MCP Server MCP server in PolicyLayer and add a rule for mark_todo_done: 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 Decision Tree MCP Server. Nothing to install.

What risk level is mark_todo_done? +

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

Can I rate-limit mark_todo_done? +

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

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

mark_todo_done is provided by the Decision Tree MCP Server MCP server (psikosen/dt_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.