Upload a local file to OneDrive
AI agents use create_file to create or update resources in Microsoft MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Microsoft MCP environment.
This tool creates or modifies data reversibly by uploading files to OneDrive cloud storage. While the action is not destructive (files can be deleted), it creates persistent data in a user's cloud account. The Write category applies because the operation is reversible and creates/stores data.
From the tool's definition Tool name 'create_file' and description 'Upload a local file to OneDrive' indicate creation of data in a cloud storage service.
Attacks that exploit this kind of access
Upload a local file to OneDrive. It is categorised as a Write tool in the Microsoft MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Microsoft MCP server in PolicyLayer and add a rule for create_file: 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 Microsoft MCP. Nothing to install.
create_file 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 create_file 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 create_file. 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.
create_file is provided by the Microsoft MCP server (purva-kashyap/microsoft-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 →