unwatch_task · Todos MCP: Risk & Policy

WHAT IT DOES

What unwatch_task does on Todos

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

WHY IT NEEDS A POLICY

Why unwatch_task needs a policy

This tool modifies a subscription/notification preference (removing a watch/subscription), which is a reversible write operation. It does not delete data, execute code, or have financial implications. The blast radius is low since it only affects notification delivery for the invoking user.

From the tool's definition Unsubscribe from notifications for a task

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

unwatch_task Rate-limited

unwatch_task 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": {
    "unwatch_task": {
      "limits": [
        {
          "counter": "unwatch_task_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 Todos, so you can run agents against it safely.

FAQ

Questions about unwatch_task

What does the unwatch_task tool do? +

Unsubscribe from notifications for a task. It is categorised as a Write tool in the Todos MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on unwatch_task? +

Register the Todos MCP server in PolicyLayer and add a rule for unwatch_task: 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 Todos. Nothing to install.

What risk level is unwatch_task? +

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

Can I rate-limit unwatch_task? +

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

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

unwatch_task is provided by the Todos MCP server (@hasna/todos). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.