查询「已完成」的提醒事项。当用户想统计/回顾过去做了什么时用它
AI agents call list_completed_reminders to retrieve information from Apple Reminders without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves historical reminder data that has already been marked complete. It has no capability to modify, delete, execute external operations, or affect financial state. The action is purely informational—listing completed reminders for review or statistics. This fits the 'Read' category: retrieves data with no side effects.
From the tool's definition Tool name 'list_completed_reminders' and description '查询（query）已完成的提醒事项' indicates retrieval of already-completed reminder data with no modification or side effects.
Attacks that exploit this kind of access
查询「已完成」的提醒事项。当用户想统计/回顾过去做了什么时用它. It is categorised as a Read tool in the Apple Reminders MCP Server, which means it retrieves data without modifying state.
Register the Apple Reminders MCP server in PolicyLayer and add a rule for list_completed_reminders: 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 Apple Reminders. Nothing to install.
list_completed_reminders 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 list_completed_reminders 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 list_completed_reminders. 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.
list_completed_reminders is provided by the Apple Reminders MCP server (yzheeng/apple-reminders-mcp-server). 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 →