Medium Risk

make_directory

Create single or multiple directories with recursive parent creation

How to control make_directory ↓

What make_directory does on Vulcan File Ops

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

Medium Risk

Why make_directory needs a policy

Creating directories is a Write operation—it modifies filesystem state but is reversible (directories can be deleted). It does not execute arbitrary code, is not destructive (can be undone), and poses no financial risk. The blast radius is medium because uncontrolled directory creation could consume disk space or clutter the filesystem, but the impact is bounded and recoverable.

From the tool's definition Tool name 'make_directory' and description 'Create single or multiple directories with recursive parent creation' explicitly perform directory creation, a reversible write operation on the filesystem.

Documented attack patterns abuse exactly the kind of access make_directory gives an agent:

How to control make_directory

PolicyLayer is an MCP gateway — it sits between your AI agents and Vulcan File Ops, and nothing reaches the server without passing your rules. This is the rule we recommend for make_directory:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "make_directory": {
      "limits": [
        {
          "counter": "make_directory_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

make_directory stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Vulcan File Ops — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about make_directory

What does the make_directory tool do? +

Create single or multiple directories with recursive parent creation. It is categorised as a Write tool in the Vulcan File Ops MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on make_directory? +

Register the Vulcan File Ops MCP server in PolicyLayer and add a rule for make_directory: 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 Vulcan File Ops. Nothing to install.

What risk level is make_directory? +

make_directory is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit make_directory? +

Yes. Add a rate_limit block to the make_directory 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.

How do I block make_directory completely? +

Set action: deny in the PolicyLayer policy for make_directory. 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.

What MCP server provides make_directory? +

make_directory is provided by the Vulcan File Ops MCP server (n0zer0d4y/vulcan-file-ops). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Vulcan File Ops tool call.

Start from Vulcan File Ops, 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.

15 Vulcan File Ops tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.