AI agents call notes_health 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.
Health checks are read-only operations that query the state of the server and application connectivity. They have no side effects, do not execute arbitrary code, do not modify data, and do not delete anything. This is a standard diagnostic tool with minimal blast radius if misused by an AI agent.
From the tool's definition Tool name 'notes_health' and description 'Check server health and Notes connectivity' indicate a diagnostic/monitoring operation that retrieves status information without modifying, executing operations, or deleting data.
Attacks that exploit this kind of access
Check server health and Notes connectivity. 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_health: 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_health 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_health 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_health. 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_health 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.
notes_health is one line of Macnotes's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →