Search reminders by text in title or notes
AI agents call search_reminders to retrieve information from Apple Reminders MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The search_reminders tool retrieves and queries existing reminder data based on text criteria. It performs a read-only operation with no side effects, no code execution, no deletions, and no financial impact. The low severity reflects minimal risk even if misused, as it only returns data the user already owns.
From the tool's definition Tool description explicitly states 'Search reminders by text in title or notes' — a query operation with no data modification.
Attacks that exploit this kind of access
Search reminders by text in title or notes. It is categorised as a Read tool in the Apple Reminders MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Apple Reminders MCP Server MCP server in PolicyLayer and add a rule for search_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 MCP Server. Nothing to install.
search_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 search_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 search_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.
search_reminders is provided by the Apple Reminders MCP Server MCP server (krishna-desiraju/apple-reminders-swift-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 →