mark_as_done · db4app Todo MCP Server MCP: Risk & Policy

WHAT IT DOES

What mark_as_done does on db4app Todo MCP Server

AI agents use mark_as_done to create or update resources in db4app Todo MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your db4app Todo MCP Server environment.

WHY IT NEEDS A POLICY

Why mark_as_done needs a policy

This tool modifies data by updating the completion status of a todo item, which is the definition of Write category. The operation is reversible (a completed task can be re-opened or the list reordered), so it does not qualify as Destructive.

From the tool's definition Tool name 'mark_as_done' combined with description 'Mark a todo item as completed' indicates a state change operation on an existing todo item. This is a reversible modification (the item can be unmarked or deleted), not a destructive action.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

mark_as_done Rate-limited

mark_as_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_as_done": {
      "limits": [
        {
          "counter": "mark_as_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 db4app Todo MCP Server, so you can run agents against it safely.

FAQ

Questions about mark_as_done

What does the mark_as_done tool do? +

Mark a todo item as completed. Use this when the user wants to complete a task. Provide the todo ID. It is categorised as a Write tool in the db4app Todo 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_as_done? +

Register the db4app Todo MCP Server MCP server in PolicyLayer and add a rule for mark_as_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 db4app Todo MCP Server. Nothing to install.

What risk level is mark_as_done? +

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

Can I rate-limit mark_as_done? +

Yes. Add a rate_limit block to the mark_as_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_as_done completely? +

Set action: deny in the PolicyLayer policy for mark_as_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_as_done? +

mark_as_done is provided by the db4app Todo MCP Server MCP server (maxabrahamsson/todo-mcp-db4app). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.