Get the current working directory
AI agents call get_current_dir to retrieve information from Command Line Interface Enhancer without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only queries the current working directory and returns its path. It has no side effects, does not execute code, and does not modify any state. It is a read-only operation that simply retrieves information about the system's current state.
From the tool's definition Get the current working directory - retrieves the current directory path without modifying state or executing external code.
Attacks that exploit this kind of access
Get the current working directory. It is categorised as a Read tool in the Command Line Interface Enhancer MCP Server, which means it retrieves data without modifying state.
Register the Command Line Interface Enhancer MCP server in PolicyLayer and add a rule for get_current_dir: 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 Command Line Interface Enhancer. Nothing to install.
get_current_dir 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_current_dir 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_current_dir. 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_current_dir is provided by the Command Line Interface Enhancer MCP server (jon2allen/mcp_command_serv). 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 →