AI agents call notes_accounts to retrieve information from Macnotes without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves/lists account names from the Notes application—a read-only operation with no side effects, no data modification, and no destructive capabilities. The action of listing existing account names is non-intrusive and carries minimal security risk, as it merely exposes metadata about configured accounts on the system.
From the tool's definition Tool name 'notes_accounts' with description 'List Notes.app account names' indicates a retrieval operation that queries account information without modifying data.
Attacks that exploit this kind of access
List Notes.app account names. It is categorised as a Read tool in the Macnotes MCP Server, which means it retrieves data without modifying state.
Register the Macnotes MCP server in PolicyLayer and add a rule for notes_accounts: 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 Macnotes. Nothing to install.
notes_accounts 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_accounts 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_accounts. 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_accounts is provided by the Macnotes MCP server (zorrobyte/macnotes-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 →