Get a note by id with normalized plaintext and optional HTML.
AI agents call notes_get 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 note content by identifier, returning data in plaintext or HTML format. It performs no side effects, creates no data, executes no code, modifies nothing, and deletes nothing. It is a straightforward read operation on local Apple Notes data, with minimal blast radius if misused by an agent (exposure of note contents only).
From the tool's definition Tool name 'notes_get' and description 'Get a note by id with normalized plaintext and optional HTML' indicate retrieval of existing data without modification or deletion.
Attacks that exploit this kind of access
Get a note by id with normalized plaintext and optional HTML. 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_get: 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_get 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_get 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_get. 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_get 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 →