Add or update a reminder on an existing event.
AI agents use set_reminder to create or update resources in Calendar Pa — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Calendar Pa environment.
The tool modifies event properties (reminders) in a reversible manner. It is not Read (it changes state), not Execute (it does not run external code or trigger complex side effects), not Destructive (reminders can be removed/updated), and not Financial. Write is appropriate.
From the tool's definition Tool description states 'Add or update a reminder on an existing event' — this creates or modifies event metadata without deleting or reversing prior state.
Attacks that exploit this kind of access
Add or update a reminder on an existing event. It is categorised as a Write tool in the Calendar Pa MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Calendar Pa MCP server in PolicyLayer and add a rule for set_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 Calendar Pa. Nothing to install.
set_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 set_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 set_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.
set_reminder is provided by the Calendar Pa MCP server (richardilemon/calendar-pa). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →