AI agents call list_directory to retrieve information from Xcode without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a directory listing operation that retrieves and displays information about files and subdirectories. It performs no data modification, deletion, code execution, or external operations. The sole purpose is information retrieval, which is characteristic of the Read category.
From the tool's definition Tool name 'list_directory' and description 'Lists the contents of a directory, showing both files and subdirectories' indicate read-only retrieval of directory structure with no modification or side effects.
Attacks that exploit this kind of access
Lists the contents of a directory, showing both files and subdirectories. It is categorised as a Read tool in the Xcode MCP Server, which means it retrieves data without modifying state.
Register the Xcode MCP server in PolicyLayer and add a rule for list_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 Xcode. Nothing to install.
list_directory 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 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. 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 is provided by the Xcode MCP server (xcode-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
list_directory is one line of Xcode's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →