AI agents use file_create 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 creation is a reversible write operation that modifies cloud storage state. While not destructive (files can be deleted), it represents a significant blast radius if an AI agent creates numerous files, overwrites shared resources, or clutters user storage. Confidence is reduced from higher due to empty description, but the tool name and server context (OneDrive management) make the Write classification clear.
From the tool's definition Tool name 'file_create' indicates file creation capability on a Microsoft 365 server managing OneDrive and related storage services.
Attacks that exploit this kind of access
file_create. 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_create: 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_create 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_create 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_create. 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_create 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 →