AI agents call folder_list 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.
The tool name 'folder_list' and the 'm365-mcp' server's management of OneDrive and Outlook indicate a read-only list operation. Without a description, confidence is moderated but the naming pattern aligns with standard read operations that retrieve data structures without modification or deletion. No destructive, financial, or code execution capability is apparent.
From the tool's definition Tool named 'folder_list' with no description provided; context from sibling tools (calendar_*, account_*, cache_*) and server purpose (manage Microsoft 365 services) suggests this lists folders in OneDrive or Outlook, which is a query/retrieval operation with…
Attacks that exploit this kind of access
folder_list. 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 folder_list: 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.
folder_list 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 folder_list 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 folder_list. 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.
folder_list is provided by the M365 MCP server (robin-collins/m365-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 →