AI agents use create_directory to create or update resources in MCP Files — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Files environment.
Directory creation modifies the filesystem by adding new structures, which qualifies as Write rather than Read. It is not Destructive because creating directories is reversible (can be removed). It is not Execute because it does not run code or trigger external operations.
From the tool's definition Tool description states "Create a directory (with parents) inside the workspace." This is a write operation that creates new filesystem structures.
Attacks that exploit this kind of access
Create a directory (with parents) inside the workspace. Immutable path rules still apply. It is categorised as a Write tool in the MCP Files MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Files 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 MCP Files. Nothing to install.
create_directory 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_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.
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.
create_directory is provided by the MCP Files MCP server (tspspi/mcpfiles). 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 →