complete_reminder · MCP Reminders MCP: Risk & Policy

WHAT IT DOES

What complete_reminder does on MCP Reminders

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

WHY IT NEEDS A POLICY

Why complete_reminder needs a policy

Completing a reminder updates metadata about that reminder's status. While it changes data, the operation is fully reversible (a completed reminder can be marked incomplete or deleted). The blast radius is minimal since reminders are low-stakes personal notes for an AI assistant across sessions. Severity is low because misuse would only clutter reminder state with no external consequences.

From the tool's definition Tool marks a reminder as 'completed', which modifies the state of an existing reminder record. The description indicates a state-change operation rather than retrieval (Read) or deletion (Destructive). This is a reversible modification.

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