AI agents call get-notebook-hierarchy to retrieve information from Onenote without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves organizational structure information from OneNote without modifying, deleting, or executing any operations. It is a safe data query that presents minimal risk even if misused by an AI agent, as it only exposes the notebook hierarchy metadata.
From the tool's definition Tool name 'get-notebook-hierarchy' and description 'Get the complete hierarchy of all notebooks, section groups, and sections' indicate a retrieval operation with no side effects.
Attacks that exploit this kind of access
Get the complete hierarchy of all notebooks, section groups, and sections. It is categorised as a Read tool in the Onenote MCP Server, which means it retrieves data without modifying state.
Register the Onenote MCP server in PolicyLayer and add a rule for get-notebook-hierarchy: 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 Onenote. Nothing to install.
get-notebook-hierarchy 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 get-notebook-hierarchy 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 get-notebook-hierarchy. 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.
get-notebook-hierarchy is provided by the Onenote MCP server (jacob-hartmann/onenote-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 →