List files and directories at a given path. Features: - List contents of any directory - Recursive listing with configurable depth - Filter results by file extension - Returns file sizes and types Use cases: - Exploring project structures - Finding specific file types - Auditing directory contents
AI agents call file_list to retrieve information from MCP Toolkit Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
file_list is a read-only operation that retrieves directory and file metadata without side effects. It poses minimal risk as it only queries filesystem metadata. Severity is low because directory listing does not inherently compromise confidentiality (though contents exposed depend on permissions) and cannot modify or execute anything. High confidence due to clear read-only semantics.
From the tool's definition Tool name and description: 'List files and directories at a given path' with features including 'List contents of any directory', 'Returns file sizes and types'. No modification, deletion, or execution occurs.
Attacks that exploit this kind of access
List files and directories at a given path. Features: - List contents of any directory - Recursive listing with configurable depth - Filter results by file extension - Returns file sizes and types Use cases: - Exploring project structures - Finding specific file types - Auditing directory contents. It is categorised as a Read tool in the MCP Toolkit Server MCP Server, which means it retrieves data without modifying state.
Register the MCP Toolkit Server MCP server in PolicyLayer and add a rule for file_list: 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 Toolkit Server. Nothing to install.
file_list 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 file_list 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 file_list. 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.
file_list is provided by the MCP Toolkit Server MCP server (vyshnavi-nandyala/mcp-toolkit-server). 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 →