List files and directories on the CNC controller
AI agents call list_sd_files to retrieve information from Cnc Fluidnc without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns a directory listing from the SD card storage of the CNC controller. It is a read-only operation that does not modify, delete, execute, or cause any state changes to the machine or its data. The blast radius if misused is minimal—an AI agent could only learn what files exist, not alter them or trigger operations.
From the tool's definition Tool name 'list_sd_files' and description 'List files and directories on the CNC controller' indicate a retrieval operation with no data modification or side effects.
Attacks that exploit this kind of access
List files and directories on the CNC controller. It is categorised as a Read tool in the Cnc Fluidnc MCP Server, which means it retrieves data without modifying state.
Register the Cnc Fluidnc MCP server in PolicyLayer and add a rule for list_sd_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 Cnc Fluidnc. Nothing to install.
list_sd_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 list_sd_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 list_sd_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.
list_sd_files is provided by the Cnc Fluidnc MCP server (whitneydesignlabs/cnc-fluidnc-mcp). 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 →