AI agents use icloud-calendar_update_event to create or update resources in Icloud — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Icloud environment.
This tool creates or modifies data in a reversible manner (calendar event metadata/scheduling). While calendar updates are not destructive, they do change user-facing data. The severity is medium because misuse could disrupt a user's schedule or cause calendar conflicts, but the effects are recoverable (events can be re-updated or restored from backups).
From the tool's definition Tool description states 'Updates an existing iCloud calendar event', which modifies data reversibly. The term 'update' is a classic Write operation. The tool operates on calendar events, a user-facing data structure.
Attacks that exploit this kind of access
Updates an existing iCloud calendar event by its CalDAV URL. It is categorised as a Write tool in the Icloud MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Icloud MCP server in PolicyLayer and add a rule for icloud-calendar_update_event: 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 Icloud. Nothing to install.
icloud-calendar_update_event 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 icloud-calendar_update_event 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 icloud-calendar_update_event. 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.
icloud-calendar_update_event is provided by the Icloud MCP server (thefredlab/icloud-mcp). 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 →