AI agents call get_directory_tree to retrieve information from Nutstore without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves directory structure information from Nutstore cloud storage with no side effects, reversible operations, or data modification. It is a pure query/list operation analogous to 'ls -R' in a file system. The low severity reflects minimal blast radius—an AI agent using this tool can only view the directory layout without affecting any files or triggering external operations.
From the tool's definition Tool name 'get_directory_tree' and description '获取坚果云目录树结构' (retrieve Nutstore directory tree structure) indicate a read-only query operation that retrieves and displays the hierarchical structure of directories without modification.
Attacks that exploit this kind of access
获取坚果云目录树结构. It is categorised as a Read tool in the Nutstore MCP Server, which means it retrieves data without modifying state.
Register the Nutstore MCP server in PolicyLayer and add a rule for get_directory_tree: 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.
get_directory_tree is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_directory_tree 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 get_directory_tree. 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.
get_directory_tree 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 →