创建文件夹
AI agents use create_folder to create or update resources in Mi Note MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mi Note MCP Server environment.
Creating a folder is a reversible data modification operation. It does not execute code, delete data, or involve financial transactions. The blast radius is low—a mistaken folder creation can be easily undone by deletion. This is a standard write operation with minimal security risk in isolation.
From the tool's definition Tool creates a new folder in Xiaomi Cloud Notes. The description '创建文件夹' (Chinese for 'create folder') and the function name 'create_folder' clearly indicate a create/write operation.
Attacks that exploit this kind of access
创建文件夹. It is categorised as a Write tool in the Mi Note MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mi Note MCP Server MCP server in PolicyLayer and add a rule for create_folder: 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 Mi Note MCP Server. Nothing to install.
create_folder 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_folder 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_folder. 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_folder is provided by the Mi Note MCP Server MCP server (laelluo/mi_note_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 →