AI agents use import_step_file to create or update resources in Kiln — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Kiln environment.
The tool creates/modifies the active design or job queue on the 3D printer system by loading external STEP geometry. This is a Write operation—it reversibly adds data to the printer's workflow. It's not Execute (doesn't directly trigger printing), Destructive (reversible), or Financial.
From the tool's definition Tool name 'import_step_file' indicates importing a 3D model file (STEP format) into a 3D printer control system. The sibling context shows tools that modify printer state and design data (add_mesh_chamfer, add_mesh_fillet, add_assembly_part, add_spool).
Attacks that exploit this kind of access
import_step_file. It is categorised as a Write tool in the Kiln MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Kiln MCP server in PolicyLayer and add a rule for import_step_file: 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.
import_step_file is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the import_step_file 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 import_step_file. 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.
import_step_file 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 →