AI agents use folder_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.
Folder renaming creates or modifies data reversibly without deletion or external code execution, fitting the Write category. Severity is medium because unintended mass folder renames in OneDrive could cause confusion and disruption, but the operation is reversible and typically limited to the authenticated user's accessible folders.
From the tool's definition Tool name 'folder_rename' indicates a modification operation on folder metadata within Microsoft 365 (likely OneDrive/SharePoint based on server scope). The empty description prevents confirmation of exact scope, but renaming is a reversible write operation.
Attacks that exploit this kind of access
folder_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 folder_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.
folder_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 folder_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 folder_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.
folder_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 →