AI agents use reminders.update_reminder to create or update resources in Nucleus Apple — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Nucleus Apple environment.
This tool modifies reminder data (e.g., title, due date, completion status) but does not delete or destroy records, making it a Write category tool. Severity is medium because misuse could corrupt user reminder data or spam/modify many reminders, but the changes are reversible via subsequent updates. Confidence is high because the intent is explicit in the name and description.
From the tool's definition Tool name is 'reminders.update_reminder' and description states 'Update an existing reminder.' The verb 'update' is a write operation that modifies existing data reversibly.
Documented attack patterns abuse exactly the kind of access reminders.update_reminder gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Nucleus Apple, and nothing reaches the server without passing your rules. This is the rule we recommend for reminders.update_reminder:
{
"version": "1",
"default": "deny",
"tools": {
"reminders.update_reminder": {
"limits": [
{
"counter": "reminders.update_reminder_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}reminders.update_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.
Free to start. No card required.
Update an existing reminder. It is categorised as a Write tool in the Nucleus Apple MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Nucleus Apple MCP server in PolicyLayer and add a rule for reminders.update_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 Nucleus Apple. Nothing to install.
reminders.update_reminder is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the reminders.update_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.
Set action: deny in the PolicyLayer policy for reminders.update_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.
reminders.update_reminder is provided by the Nucleus Apple MCP server (zish-rob-crur/nucleus-apple-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Nucleus Apple, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
30 Nucleus Apple tools catalogued and risk-classified — across an index of 43,000+ MCP servers.