Medium Risk

create_directories

Create multiple specified directories (including intermediate ones).

How to control create_directories ↓

What create_directories does on Filesystem

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

Medium Risk

Why create_directories needs a policy

Creating directories is a write operation that modifies the file system structure. While not destructive (directories can be deleted), it irreversibly changes the file system state. Severity is medium rather than high because directory creation is a common, low-blast-radius operation compared to deleting or overwriting critical files, though it could enable further harmful operations.

From the tool's definition Tool creates directories (irreversible file system operations that persist on disk). Tool name 'create_directories' explicitly states creation action. Description states 'Create multiple specified directories (including intermediate ones).'

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

How to control create_directories

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

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

create_directories 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 Filesystem — 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 create_directories

What does the create_directories tool do? +

Create multiple specified directories (including intermediate ones). It is categorised as a Write tool in the Filesystem MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on create_directories? +

Register the Filesystem MCP server in PolicyLayer and add a rule for create_directories: 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 Filesystem. Nothing to install.

What risk level is create_directories? +

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

Can I rate-limit create_directories? +

Yes. Add a rate_limit block to the create_directories 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 create_directories completely? +

Set action: deny in the PolicyLayer policy for create_directories. 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 create_directories? +

create_directories is provided by the Filesystem MCP server (sylphxai/filesystem-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Filesystem tool call.

Start from Filesystem, 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.

13 Filesystem 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.