AI agents call step_file_info to retrieve information from Kiln without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
STEP is a standard CAD file format. A tool named 'step_file_info' almost certainly retrieves or analyzes file properties (dimensions, parameters, structure) without modifying or executing anything. The lack of verbs like 'modify', 'delete', or 'execute' in the name, combined with the context of design analysis tools ('analyze_design_requirements') on this server, suggests read-only information retrieval.
From the tool's definition Tool name 'step_file_info' suggests retrieval of metadata or information about STEP files (a common CAD format). No description provided, but the naming convention and context of a 3D printer control system indicate a query/inspection operation.
Attacks that exploit this kind of access
step_file_info. It is categorised as a Read tool in the Kiln MCP Server, which means it retrieves data without modifying state.
Register the Kiln MCP server in PolicyLayer and add a rule for step_file_info: 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 Kiln. Nothing to install.
step_file_info 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 step_file_info 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 step_file_info. 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.
step_file_info is provided by the Kiln MCP server (codeofaxel/Kiln). 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 →