AI agents call list-notebooks 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.
The tool retrieves and queries notebook metadata accessible to the authenticated user. It has no side effects, does not modify state, and serves a discovery/read purpose. The blast radius of misuse is minimal — an agent could enumerate notebooks but cannot alter or delete them. Severity is low because access is already authenticated and the information returned is metadata the user has legitimate access to view.
From the tool's definition Tool description states it 'List[s] all OneNote notebooks' and 'Returns notebook names, IDs, and metadata' — purely retrieval operations with no modification or side effects.
Attacks that exploit this kind of access
List all OneNote notebooks accessible to the authenticated user. Returns notebook names, IDs, and metadata. Use this to discover available notebooks before accessing sections or pages. 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 list-notebooks: 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.
list-notebooks 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 list-notebooks 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 list-notebooks. 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.
list-notebooks 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 →