AI agents use file_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.
File renaming is a write operation that modifies file metadata reversibly. It does not delete data (ruling out Destructive) nor move money (ruling out Financial). The lack of a tool description reduces confidence slightly, but the name and server context (OneDrive file management) clearly indicate a Write capability.
From the tool's definition Tool name 'file_rename' indicates modification of file metadata (renaming files). The tool operates within Microsoft 365's file management context (OneDrive). No destructive deletion occurs, but the operation is reversible and modifies data state.
Attacks that exploit this kind of access
file_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 file_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.
file_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 file_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 file_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.
file_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 →