AI agents call listDir to retrieve information from Shell MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries filesystem metadata and returns directory contents. It is a read-only operation with no side effects—no data is created, modified, deleted, or executed. The blast radius is minimal; the worst outcome is information disclosure about directory structure. While this server as a whole enables powerful operations (exec, deleteFile, writeFile), this particular tool is purely informational.
From the tool's definition Tool name 'listDir' and description 'List the contents of a directory with metadata for each entry' indicate a directory listing operation that retrieves information without modifying or executing anything.
Attacks that exploit this kind of access
List the contents of a directory with metadata for each entry. It is categorised as a Read tool in the Shell MCP MCP Server, which means it retrieves data without modifying state.
Register the Shell MCP server in PolicyLayer and add a rule for listDir: 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 Shell MCP. Nothing to install.
listDir 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 listDir 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 listDir. 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.
listDir is provided by the Shell MCP server (lucivuc/shell-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 →