AI agents call list_directories to retrieve information from Demo without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries the filesystem to retrieve directory listings within a constrained root directory (MCP_FILE_OPS_ROOT). It has no side effects, does not execute commands, and does not modify data. It is purely informational, making it a Read category tool with low severity since directory listing within a sandbox poses minimal risk.
From the tool's definition Tool name 'list_directories' and description 'List directories directly inside a folder' indicate a retrieval operation with no modification or execution of code.
Attacks that exploit this kind of access
List directories directly inside a folder within MCP_FILE_OPS_ROOT. It is categorised as a Read tool in the Demo MCP Server, which means it retrieves data without modifying state.
Register the Demo MCP server in PolicyLayer and add a rule for list_directories: 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 Demo. Nothing to install.
list_directories 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_directories 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_directories. 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_directories is provided by the Demo MCP server (penguinszp001/mcp-server-demo). 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 →