# runbox_list_directory

List all direct children in a directory in an existing code sandbox, non recursive, linux debian VM

Agent View of the PolicyLayer registry record for `runbox_list_directory`. HTML page: https://policylayer.com/tools/11cafe-website-publisher-mcp/runbox-list-directory

## Facts

- Tool: `runbox_list_directory`
- Server: Runbox Website Builder MCP (`11cafe/website-publisher-mcp`) — https://policylayer.com/tools/11cafe-website-publisher-mcp.md
- Homepage: https://github.com/11cafe/website-publisher-mcp
- Risk category: Read (Low risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Allowed

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "runbox_list_directory",
    "arguments": {}
  }
}
```

## Why runbox_list_directory is rated Low

This tool only retrieves directory contents without side effects, matching the Read category definition. The blast radius is minimal: exposure of this tool allows an attacker to discover file structure but cannot modify, delete, or execute code. Severity is low because directory enumeration alone presents limited risk compared to write, execute, or destructive operations on the same server.

From the tool's own definition: "Tool name contains 'list' and description states 'List all direct children in a directory' — core read operation with no modification or execution capability. The non-recursive scope and read-only nature further confirm this."

## Use case

AI agents call runbox_list_directory to retrieve information from Runbox Website Builder MCP without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

## Recommended policy (PolicyLayer)

Verdict: **Allowed**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Runbox Website Builder MCP:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "runbox_list_directory": {}
  }
}
```

## Other tools on Runbox Website Builder MCP (6)

- `runbox_create_sandbox` — Execute — https://policylayer.com/tools/11cafe-website-publisher-mcp/runbox-create-sandbox.md
- `runbox_execute_command` — Execute — https://policylayer.com/tools/11cafe-website-publisher-mcp/runbox-execute-command.md
- `runbox_expose_port` — Execute — https://policylayer.com/tools/11cafe-website-publisher-mcp/runbox-expose-port.md
- `runbox_serve_static_website` — Execute — https://policylayer.com/tools/11cafe-website-publisher-mcp/runbox-serve-static-website.md
- `runbox_read_file` — Read — https://policylayer.com/tools/11cafe-website-publisher-mcp/runbox-read-file.md
- `runbox_write_file` — Write — https://policylayer.com/tools/11cafe-website-publisher-mcp/runbox-write-file.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=11cafe-website-publisher-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/11cafe-website-publisher-mcp