AI agents use create_dir to create or update resources in Context — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Context environment.
Directory creation is a reversible write operation—directories can be deleted or their contents modified without permanent loss. The tool does not execute arbitrary code, delete data, or cause financial impact. The low severity reflects minimal blast radius since directory creation on its own causes no destructive effects; the tool operates safely and idempotently. This is a standard file system Write operation.
From the tool's definition The tool 'create_dir' creates a directory structure, which is a reversible modification operation. The description states it 'Create[s] a directory (and any missing parent directories)' and is 'Safe to call if already exists', indicating idempotent behavior…
Attacks that exploit this kind of access
Create a directory (and any missing parent directories). Safe to call if already exists. It is categorised as a Write tool in the Context MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Context MCP server in PolicyLayer and add a rule for create_dir: 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 Context. Nothing to install.
create_dir is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_dir 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.
Set action: deny in the PolicyLayer policy for create_dir. 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.
create_dir is provided by the Context MCP server (vibhasdutta/context-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →