list_directories_by_size
AI agents call list_directories_by_size to retrieve information from Linux MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves directory size information for diagnostic purposes with no capacity to modify, delete, or execute operations. It aligns with the server's read-only diagnostic mission. The empty description lowers confidence slightly, but the naming and sibling context strongly indicate a passive query operation with zero side effects.
From the tool's definition Tool name 'list_directories_by_size' combined with server description stating 'read-only Linux system diagnostics' and sibling tools that all perform non-destructive queries (get_audit_logs, get_disk_usage, get_hardware_info, etc.).
Attacks that exploit this kind of access
list_directories_by_size. It is categorised as a Read tool in the Linux MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Linux MCP Server MCP server in PolicyLayer and add a rule for list_directories_by_size: 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 Linux MCP Server. Nothing to install.
list_directories_by_size 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_by_size 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_by_size. 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_by_size is provided by the Linux MCP Server MCP server (narmaku/linux-mcp-server-archived). 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 →