AI agents call fs_list_files to retrieve information from LocalAnt without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a directory listing operation, which is a non-destructive query that retrieves information about files without side effects. It does not create, modify, delete, or execute anything. The allowlist restriction further limits blast radius by constraining which directories can be accessed. Severity is low because even with unrestricted use, directory listing poses minimal risk to system integrity.
From the tool's definition Tool name 'fs_list_files' and description 'List files in a directory inside the allowlist' indicate a read-only operation that retrieves directory contents without modifying, deleting, or executing anything.
Attacks that exploit this kind of access
List files in a directory inside the allowlist. It is categorised as a Read tool in the LocalAnt MCP Server, which means it retrieves data without modifying state.
Register the LocalAnt MCP server in PolicyLayer and add a rule for fs_list_files: 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 LocalAnt. Nothing to install.
fs_list_files 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 fs_list_files 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 fs_list_files. 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.
fs_list_files is provided by the LocalAnt MCP server (yuga-hashimoto/localant). 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 →