Search note titles and plaintext bodies.
AI agents call notes_search to retrieve information from Apple Notes MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries data from Apple Notes without side effects. Searching note content is a read-only operation that does not create, modify, delete, execute commands, or involve financial transactions. The low severity reflects minimal blast radius if misused by an AI agent — at worst, it could reveal sensitive note contents to which the agent already has access.
From the tool's definition Tool name is 'notes_search' and description states it 'Search note titles and plaintext bodies' — a query operation with no modification or deletion capability.
Attacks that exploit this kind of access
Search note titles and plaintext bodies. It is categorised as a Read tool in the Apple Notes MCP MCP Server, which means it retrieves data without modifying state.
Register the Apple Notes MCP server in PolicyLayer and add a rule for notes_search: 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 Notes MCP. Nothing to install.
notes_search 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 notes_search 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 notes_search. 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.
notes_search is provided by the Apple Notes MCP server (renatoaraujo/apple-notes-mcp). 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 →