View the contents of a saved macro.
AI agents call get_macro 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 retrieves and displays existing macro data without modifying, executing, or deleting anything. It is a straightforward query operation that does not alter machine state or execute code. Even in the context of a CNC machine controller, reading macro definitions poses minimal risk compared to tools that execute or modify configurations. The blast radius is limited to information disclosure of macro content.
From the tool's definition Tool name is 'get_macro' and description states 'View the contents of a saved macro' — a read-only retrieval operation with no side effects.
Attacks that exploit this kind of access
View the contents of a saved macro. 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 get_macro: 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.
get_macro 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 get_macro 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 get_macro. 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.
get_macro 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 →