Create a new directory or ensure a directory exists. Can create multiple
AI agents use create_directory to create or update resources in Search — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Search environment.
This tool creates or modifies filesystem state by establishing new directories. It is reversible (directories can be deleted), so it falls under Write rather than Destructive. The severity is medium because uncontrolled directory creation could fill disk space or create unexpected filesystem structures, but the impact is limited compared to data deletion or code execution.
From the tool's definition Tool name 'create_directory' and description 'Create a new directory or ensure a directory exists' indicate creation/modification of filesystem structures.
Documented attack patterns abuse exactly the kind of access create_directory gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Search, and nothing reaches the server without passing your rules. This is the rule we recommend for create_directory:
{
"version": "1",
"default": "deny",
"tools": {
"create_directory": {
"limits": [
{
"counter": "create_directory_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}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.
Free to start. No card required.
Create a new directory or ensure a directory exists. Can create multiple. It is categorised as a Write tool in the Search MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Search 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 Search. 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 Search MCP server (@agent-infra/mcp-server-search). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Search, 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.
36 Search tools catalogued and risk-classified — across an index of 43,000+ MCP servers.