AI agents call folder_get_tree 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 tool appears to retrieve folder structure information, likely from OneDrive or another M365 file service. No modification, deletion, or execution occurs. The empty description reduces confidence slightly, but the naming convention strongly suggests a read-only hierarchical query. The blast radius of misuse is limited to data disclosure of folder structure, making it low severity.
From the tool's definition Tool name 'folder_get_tree' suggests retrieval of a folder hierarchy structure. The 'get' verb and '_tree' suffix indicate a query operation that returns data without modification.
Attacks that exploit this kind of access
folder_get_tree. 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_get_tree: 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_get_tree 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_get_tree 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_get_tree. 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_get_tree 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.
folder_get_tree is one line of M365's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →