AI agents use create_directory to create or update resources in Nutstore — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Nutstore environment.
Creating a directory is a write operation that modifies cloud storage structure. It is reversible (unlike destructive operations) and has no financial impact or code execution. Severity is medium due to potential misuse creating numerous directories consuming storage quota or cluttering the filesystem, but with limited blast radius since the operation is easily undone.
From the tool's definition Tool description indicates 'create_directory' creates new directories in Nutstore cloud storage. The action is reversible (directories can be deleted), and creates/modifies the file system state.
Attacks that exploit this kind of access
在坚果云中创建新目录. It is categorised as a Write tool in the Nutstore MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Nutstore MCP server in PolicyLayer and add a rule for create_directory: 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 Nutstore. Nothing to install.
create_directory 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_directory 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_directory. 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_directory is provided by the Nutstore MCP server (silverze/nutstore-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 →