Explores directory structure in VS Code workspace. WHEN TO USE: Understanding project structure, finding files before read/modify operations. CRITICAL: NEVER set recursive=true on root directory (.) - output too large. Use recursive only on specific subdirectories. Returns files and directories a...
AI agents call list_files_code to retrieve information from Vscode 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 the directory structure without creating, modifying, deleting, or executing any changes. It is purely informational and is explicitly positioned as a precursor to other operations. The blast radius of misuse is minimal—an agent could at worst explore the workspace structure, which reveals information but causes no damage or unintended modifications.
From the tool's definition Tool 'list_files_code' with description states it 'Explores directory structure' and 'Returns files and directories at specified path.' The guidance explicitly states to use it for 'Understanding project structure, finding files before read/modify…
Risk signalsAdmin/system-level operation
Documented attack patterns abuse exactly the kind of access list_files_code gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Vscode, and nothing reaches the server without passing your rules. This is the rule we recommend for list_files_code:
{
"version": "1",
"default": "deny",
"tools": {
"list_files_code": {}
}
}list_files_code is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Explores directory structure in VS Code workspace. WHEN TO USE: Understanding project structure, finding files before read/modify operations. CRITICAL: NEVER set recursive=true on root directory (.) - output too large. Use recursive only on specific subdirectories. Returns files and directories at specified path. Start with path=. It is categorised as a Read tool in the Vscode MCP Server, which means it retrieves data without modifying state.
Register the Vscode MCP server in PolicyLayer and add a rule for list_files_code: 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 Vscode. Nothing to install.
list_files_code 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_files_code 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_files_code. 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_files_code is provided by the Vscode MCP server (juehang/vscode-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Vscode, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
12 Vscode tools catalogued and risk-classified — across an index of 43,000+ MCP servers.