Append content to an Apple Note or preview the mutation with dryRun.
AI agents use append_note to create or update resources in MCP Apple Notes — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Apple Notes environment.
Appending content to a note is a write operation that modifies existing data. It is reversible (content can be removed), so it falls under Write rather than Destructive. The dryRun option further confirms this is a mutation with a preview safeguard. Misuse could lead to unwanted modification of notes, giving it medium severity.
From the tool's definition 'Append content to an Apple Note' — modifies an existing note by adding data; 'dryRun' option implies reversible mutation
Attacks that exploit this kind of access
Append content to an Apple Note or preview the mutation with dryRun. It is categorised as a Write tool in the MCP Apple Notes MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Apple Notes MCP server in PolicyLayer and add a rule for append_note: 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 Notes. Nothing to install.
append_note is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the append_note 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 append_note. 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.
append_note is provided by the MCP Apple Notes MCP server (noahshrader/mcp-apple-notes). 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 →