drop_todo · UnClick MCP: Risk & Policy

WHAT IT DOES

What drop_todo does on UnClick

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

PARAMETERS

Parameter	Type	Required	Description
`todo_id`	string	Yes
`agent_id`	string	Yes

Parameters from the server's own tool schema.

WHY IT NEEDS A POLICY

Why drop_todo needs a policy

The tool updates the state of a todo item to 'dropped' rather than permanently deleting it. Since history is preserved and the description explicitly states it is not a delete, this is a reversible Write operation. The blast radius is low as it only affects a single todo item's status.

From the tool's definition 'Marks a todo as dropped' and 'Soft state, not a delete' — explicitly confirms this is a reversible status change, not a deletion.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

drop_todo Rate-limited

drop_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": {
    "drop_todo": {
      "limits": [
        {
          "counter": "drop_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 UnClick, so you can run agents against it safely.

FAQ

Questions about drop_todo

What does the drop_todo tool do? +

Marks a todo as dropped (decided not to do it). Soft state, not a delete. Use when a todo is obsolete but the history still matters. agent_id required. It is categorised as a Write tool in the UnClick MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

What parameters does drop_todo accept? +

drop_todo accepts 2 parameters: todo_id, agent_id. Required: todo_id, agent_id. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on drop_todo? +

Register the UnClick MCP server in PolicyLayer and add a rule for drop_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 UnClick. Nothing to install.

What risk level is drop_todo? +

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

Can I rate-limit drop_todo? +

Yes. Add a rate_limit block to the drop_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 drop_todo completely? +

Set action: deny in the PolicyLayer policy for drop_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 drop_todo? +

drop_todo is provided by the UnClick MCP server (@unclick/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.