folder_delete
AI agents call folder_delete to permanently remove resources in M365 — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Folder deletion is an irreversible operation that destroys data without recovery options in typical M365 workflows. This qualifies as Destructive rather than Write (which is reversible). High severity due to potential loss of user data, calendar items, emails, or documents.
From the tool's definition Tool name 'folder_delete' indicates irreversible deletion of a folder. The empty description prevents confirmation of scope, but the semantic meaning of 'delete' combined with the Microsoft 365 context (where folders contain emails, documents, or other data)…
Attacks that exploit this kind of access
folder_delete. It is categorised as a Destructive tool in the M365 MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the M365 MCP server in PolicyLayer and add a rule for folder_delete: 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_delete is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the folder_delete 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_delete. 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_delete 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 →