emailfolders_delete
AI agents call emailfolders_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.
Email folder deletion is an irreversible operation that permanently removes data and cannot be undone by the user through normal means. This qualifies as Destructive rather than Write. The impact is significant (high severity) as an AI agent accidentally deleting important email folders could result in permanent data loss. High confidence despite empty description because the function name is unambiguous.
From the tool's definition Tool name 'emailfolders_delete' explicitly indicates deletion of email folders. The verb 'delete' combined with 'emailfolders' indicates irreversible removal of data.
Attacks that exploit this kind of access
emailfolders_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 emailfolders_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.
emailfolders_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 emailfolders_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 emailfolders_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.
emailfolders_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 →