List all configured screenshot directories
AI agents call list_directories to retrieve information from MCP Windows Screenshots without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves configuration information about screenshot storage locations. While it is fundamentally a read operation (no data modification), the medium severity reflects that enumerating system directories could reveal file system paths, storage structure, and potentially sensitive location data that could inform further reconnaissance by a misused agent.
From the tool's definition Tool name 'list_directories' and description 'List all configured screenshot directories' indicate a query/retrieval operation with no side effects.
Documented attack patterns abuse exactly the kind of access list_directories gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Windows Screenshots, and nothing reaches the server without passing your rules. This is the rule we recommend for list_directories:
{
"version": "1",
"default": "deny",
"tools": {
"list_directories": {}
}
}list_directories is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
List all configured screenshot directories. It is categorised as a Read tool in the MCP Windows Screenshots MCP Server, which means it retrieves data without modifying state.
Register the MCP Windows Screenshots MCP server in PolicyLayer and add a rule for list_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 MCP Windows Screenshots. Nothing to install.
list_directories is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list_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.
Set action: deny in the PolicyLayer policy for list_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.
list_directories is provided by the MCP Windows Screenshots MCP server (rubinsh/mcp-windows-screenshots). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP Windows Screenshots, 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.
3 MCP Windows Screenshots tools catalogued and risk-classified — across an index of 43,000+ MCP servers.