get_subtasks
AI agents call get_subtasks 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.
The 'get_subtasks' tool retrieves subtask data with no modification or deletion. While the tool description is empty, the name clearly indicates a read operation that queries existing reminder subtasks. This poses minimal security risk as it only retrieves data without side effects. Severity is low because misuse would only expose reminder details, not create, modify, or destroy data.
From the tool's definition Tool name 'get_subtasks' indicates retrieval of subtask data. Server description confirms the MCP Apple Reminders server exposes 'read' operations including retrieval of reminders and related data.
Attacks that exploit this kind of access
get_subtasks. 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_subtasks: 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_subtasks 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_subtasks 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_subtasks. 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_subtasks 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 →