AI agents call list_directory to retrieve information from Claude Context Local without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves directory structure/contents without modifying or executing anything. No side effects. Sibling tools confirm the server is designed for indexing and searching codebases, where listing directories is a natural read operation. Low severity because it only exposes file/folder metadata and structure.
From the tool's definition Tool name 'list_directory' indicates directory enumeration. Description is empty, but naming and sibling tools (read_file, directory_tree, search_codebase) indicate this is a read-only information retrieval function for exploring local codebase structure.
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 Claude Context Local, 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 Claude Context Local MCP Server, which means it retrieves data without modifying state.
Register the Claude Context Local 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 Claude Context Local. 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 Claude Context Local MCP server (mikeo-ai/claude-context-local). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Claude Context Local, 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.
9 Claude Context Local tools catalogued and risk-classified — across an index of 43,000+ MCP servers.