AI agents call list_directory_tree to retrieve information from Sysprobe without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries directory structure metadata without side effects. It is a passive read operation that lists files and their sizes, analogous to `ls` or `find` commands used for inspection. The bounded depth and entry limits further constrain its scope, making it low-risk even if misused by an agent. No data is created, modified, deleted, or executed.
From the tool's definition Tool description explicitly states it provides 'Compact directory tree (names + sizes)' with bounded depth and entries—purely retrieval of filesystem structure information with no modification, deletion, or execution capability.
Attacks that exploit this kind of access
Compact directory tree (names + sizes), depth/entry-bounded. It is categorised as a Read tool in the Sysprobe MCP Server, which means it retrieves data without modifying state.
Register the Sysprobe MCP server in PolicyLayer and add a rule for list_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 Sysprobe. Nothing to install.
list_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 list_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 list_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.
list_directory_tree is provided by the Sysprobe MCP server (raindancer118/sysprobe-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 →