List ALL sections across ALL notebooks.
AI agents call list_all_sections to retrieve information from OneNote MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves organizational metadata (section names/structure) from OneNote notebooks without creating, modifying, or deleting any data. It has no side effects and poses minimal risk if misused by an agent—an attacker gains only visibility into notebook structure, not access to sensitive content or the ability to alter data.
From the tool's definition Tool name and description indicate listing/querying sections across notebooks. The verb 'list' and absence of any modification language ('create', 'delete', 'modify', 'append') confirm retrieval only.
Attacks that exploit this kind of access
List ALL sections across ALL notebooks. It is categorised as a Read tool in the OneNote MCP Server MCP Server, which means it retrieves data without modifying state.
Register the OneNote MCP Server MCP server in PolicyLayer and add a rule for list_all_sections: 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 MCP Server. Nothing to install.
list_all_sections 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_all_sections 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_all_sections. 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_all_sections is provided by the OneNote MCP Server MCP server (mhzarem/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 →