AI agents use notes_update to create or update resources in Macnotes — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Macnotes environment.
This tool modifies existing notes (title and/or body content) but does not delete or irreversibly destroy data. The 'queued background write' design suggests the operation is reversible—users can update again to correct mistakes. It affects only the user's own notes data without financial implications or code execution, placing it in the Write category.
From the tool's definition Tool name 'notes_update' and description stating it 'Update note title/body (queued background write by default)' explicitly indicates modification of existing data.
Attacks that exploit this kind of access
Update note title/body (queued background write by default). It is categorised as a Write tool in the Macnotes MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Macnotes MCP server in PolicyLayer and add a rule for notes_update: 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_update 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 notes_update 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_update. 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_update 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 →