AI agents call mail_list_folders to retrieve information from M365 without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a data retrieval operation that enumerates mailbox folder structure and message statistics. While it does not create, modify, or delete data, the medium severity reflects that an AI agent could exploit folder enumeration to discover sensitive mailbox structures, identify high-value targets for further compromise, or map organizational communication patterns.
From the tool's definition The tool "list mail folders" retrieves folder metadata including unread/total message counts without modifying any data. The description explicitly states it "list[s] mail folders" and supports browsing via parameters, which are hallmark Read operations.
Attacks that exploit this kind of access
List mail folders in a Microsoft 365 mailbox with unread/total message counts. Supports browsing subfolders via parent_folder_id. Supports shared mailboxes via the mailbox parameter. It is categorised as a Read tool in the M365 MCP Server, which means it retrieves data without modifying state.
Register the M365 MCP server in PolicyLayer and add a rule for mail_list_folders: 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 M365. Nothing to install.
mail_list_folders 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 mail_list_folders 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 mail_list_folders. 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.
mail_list_folders is provided by the M365 MCP server (swamirama/m365-mcp-server). 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 →