# create_directory

Create a directory. Creates parent directories if they don't exist.

Agent View of the PolicyLayer registry record for `create_directory`. HTML page: https://policylayer.com/tools/deep-ai-kr-dev-mcp/create-directory

## Facts

- Tool: `create_directory`
- Server: Dev (`deep-ai-kr/dev-mcp`) — https://policylayer.com/tools/deep-ai-kr-dev-mcp.md
- Homepage: https://github.com/deep-ai-kr/dev-mcp
- Risk category: Write (Medium risk)
- Registry record: grade C, identity unverified
- Server rate-limited: no
- Parameters: 1
- Recommended policy verdict: Rate-limited

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `path` | string | no | Path to the directory to create (relative to root) |

Parameters from the server's own tool schema.

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

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

## Why create_directory is rated Medium

This tool creates new directories within the configured root. Directory creation is a reversible write operation—directories can be subsequently deleted. It does not delete data, execute arbitrary code, or trigger destructive operations. The blast radius is limited to filesystem organization within the safe, configurable root boundary described in the server's purpose.

From the tool's own definition: "Tool description states it 'Create[s] a directory' and 'Creates parent directories if they don't exist.' The action is file system modification that creates new directories reversibly (directories can be deleted)."

Risk signals: Accepts file system path (path)

## Use case

AI agents use create_directory to create or update resources in Dev, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Dev environment.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches Dev:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "create_directory": {
      "limits": [
        {
          "counter": "create_directory_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on Dev (6)

- `get_file_info` — Read — https://policylayer.com/tools/deep-ai-kr-dev-mcp/get-file-info.md
- `list_directory` — Read — https://policylayer.com/tools/deep-ai-kr-dev-mcp/list-directory.md
- `read_text_file` — Read — https://policylayer.com/tools/deep-ai-kr-dev-mcp/read-text-file.md
- `search_files` — Read — https://policylayer.com/tools/deep-ai-kr-dev-mcp/search-files.md
- `move_file` — Write — https://policylayer.com/tools/deep-ai-kr-dev-mcp/move-file.md
- `write_file` — Write — https://policylayer.com/tools/deep-ai-kr-dev-mcp/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=deep-ai-kr-dev-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/deep-ai-kr-dev-mcp