AI agents call list_directory to retrieve information from Polycodegraph without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Lists directory contents without modification. No side effects, data retrieval only. Severity is low because directory enumeration poses minimal risk in code analysis contexts; blast radius is limited to information disclosure of file/folder structure.
From the tool's definition Tool name 'list_directory' indicates directory enumeration; empty description limits direct evidence, but context from sibling tools (grep, read_file) suggests query-oriented operations.
Documented attack patterns abuse exactly the kind of access list_directory gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Polycodegraph, and nothing reaches the server without passing your rules. This is the rule we recommend for list_directory:
{
"version": "1",
"default": "deny",
"tools": {
"list_directory": {}
}
}list_directory 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_directory. It is categorised as a Read tool in the Polycodegraph MCP Server, which means it retrieves data without modifying state.
Register the Polycodegraph MCP server in PolicyLayer and add a rule for list_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 Polycodegraph. Nothing to install.
list_directory 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_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 list_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.
list_directory is provided by the Polycodegraph MCP server (smochan/polycodegraph). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Polycodegraph, 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 Polycodegraph tools catalogued and risk-classified — across an index of 43,000+ MCP servers.