complete_reminder · Reminders MCP: Risk & Policy

WHAT IT DOES

What complete_reminder does on Reminders

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

WHY IT NEEDS A POLICY

Why complete_reminder needs a policy

This tool modifies data reversibly by changing a reminder's completion status. It does not delete or destroy data (would be Destructive), nor does it execute arbitrary code (would be Execute). The change is reversible—a reminder can be marked incomplete again. The blast radius is minimal: worst case, reminders show incorrect completion status but remain recoverable. This is a standard Write operation.

From the tool's definition Tool name 'complete_reminder' and description 'Mark a reminder as completed' indicate a state change operation that modifies the reminder's status from incomplete to complete.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

complete_reminder Rate-limited

complete_reminder 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_reminder": {
      "limits": [
        {
          "counter": "complete_reminder_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 Reminders, so you can run agents against it safely.

FAQ

Questions about complete_reminder

What does the complete_reminder tool do? +

Mark a reminder as completed. It is categorised as a Write tool in the Reminders 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_reminder? +

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

What risk level is complete_reminder? +

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

Can I rate-limit complete_reminder? +

Yes. Add a rate_limit block to the complete_reminder 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_reminder completely? +

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

complete_reminder is provided by the Reminders MCP server (walalabs/reminders-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.