search_calendars
AI agents call search_calendars 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.
Searching calendars is a data retrieval operation with no side effects. Even though the description is empty, the name and context clearly indicate this is a read-only query operation. The low severity reflects minimal blast radius—calendar metadata exposure poses minimal risk compared to destructive or execute actions.
From the tool's definition Tool name 'search_calendars' indicates a search/query operation. The broader server description mentions 'search' as a read capability alongside create, read, update, delete operations. No description provided for this specific tool, lowering confidence.
Attacks that exploit this kind of access
search_calendars. 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 search_calendars: 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.
search_calendars 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 search_calendars 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 search_calendars. 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.
search_calendars 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 →