complete_todo · MCP Personal Assistant MCP: Risk & Policy

WHAT IT DOES

What complete_todo does on MCP Personal Assistant

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

WHY IT NEEDS A POLICY

Why complete_todo needs a policy

This tool modifies data reversibly—a completed todo can be marked incomplete again. It is not destructive (data is preserved), not execute (no arbitrary code/commands), and not financial. The modification is localized to a single todo item with minimal blast radius if misused by an AI agent. Classified as Write with low severity.

From the tool's definition Tool name 'complete_todo' and description 'Mark a todo as completed' indicate a state modification operation that updates an existing record (from incomplete to complete status) without deleting or destroying data.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

complete_todo Rate-limited

complete_todo 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": {
    "complete_todo": {
      "limits": [
        {
          "counter": "complete_todo_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 Personal Assistant, so you can run agents against it safely.

FAQ

Questions about complete_todo

What does the complete_todo tool do? +

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

How do I enforce a policy on complete_todo? +

Register the MCP Personal Assistant MCP server in PolicyLayer and add a rule for complete_todo: 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 Personal Assistant. Nothing to install.

What risk level is complete_todo? +

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

Can I rate-limit complete_todo? +

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

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

complete_todo is provided by the MCP Personal Assistant MCP server (swapnilsurdi/mcp-pa). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.