AI agents use emailfolders_rename to create or update resources in M365 — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your M365 environment.
Renaming an email folder modifies data (the folder metadata) but does not delete data or cause irreversible changes—users can rename folders back if needed. This is a Write category operation. Severity is medium because misuse could disorganize a user's email structure or cause confusion, but the impact is limited to folder naming and is easily reversible.
From the tool's definition Tool name 'emailfolders_rename' indicates modification of email folder names. The server manages Microsoft 365 Outlook, and renaming folders is a reversible write operation on email organization metadata.
Attacks that exploit this kind of access
emailfolders_rename. It is categorised as a Write tool in the M365 MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the M365 MCP server in PolicyLayer and add a rule for emailfolders_rename: 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_rename is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the emailfolders_rename 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_rename. 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_rename 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 →