create_directory · Server Sequential Thinking MCP

WHAT IT DOES

What create_directory does on Server Sequential Thinking

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

WHY IT NEEDS A POLICY

Why create_directory needs a policy

Creating directories is a reversible write operation—directories can be deleted, so it does not meet the threshold for Destructive classification. The blast radius is low since directory creation does not affect existing data or critical operations directly. It belongs in Write rather than Execute because it has a clear, bounded purpose (directory creation) rather than executing arbitrary code or external operations.

From the tool's definition Tool description states 'Create a new directory or ensure a directory exists,' which creates new filesystem objects. This is explicitly a write operation that modifies the filesystem state reversibly.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

create_directory Rate-limited

create_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.

View as policy code

policy.json

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

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Server Sequential Thinking, so you can run agents against it safely.

FAQ

Questions about create_directory

What does the create_directory tool do? +

Create a new directory or ensure a directory exists. Can create multiple. It is categorised as a Write tool in the Server Sequential Thinking 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_directory? +

Register the Server Sequential Thinking MCP server in PolicyLayer and add a rule for create_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 Server Sequential Thinking. Nothing to install.

What risk level is create_directory? +

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

Can I rate-limit create_directory? +

Yes. Add a rate_limit block to the create_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 create_directory completely? +

Set action: deny in the PolicyLayer policy for create_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 create_directory? +

create_directory is provided by the Server Sequential Thinking MCP server (@modelcontextprotocol/server-sequential-thinking). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.