get_recently_deleted
AI agents call get_recently_deleted to retrieve information from MCP Apple Reminders without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves historical data about deleted reminders rather than executing external operations, modifying data, or causing financial effects. It reads from a 'recently deleted' container, which is a standard read operation. The lack of description slightly reduces confidence, but the naming convention and server context make the categorization clear.
From the tool's definition Tool name 'get_recently_deleted' indicates retrieval of deleted reminders from a trash/recycle bin. The server description confirms read operations are supported. No description provided, but the pattern is consistent with query-style retrieval.
Attacks that exploit this kind of access
get_recently_deleted. It is categorised as a Read tool in the MCP Apple Reminders MCP Server, which means it retrieves data without modifying state.
Register the MCP Apple Reminders MCP server in PolicyLayer and add a rule for get_recently_deleted: 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 Apple Reminders. Nothing to install.
get_recently_deleted is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_recently_deleted 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 get_recently_deleted. 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.
get_recently_deleted is provided by the MCP Apple Reminders MCP server (rex/mcp-apple-reminders). 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 →