AI agents use update_scad_parameter 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 modifies design parameters (reversibly) rather than executing print operations or deleting data. While the empty description reduces confidence, the 'update' action combined with SCAD parameter context suggests data modification (Write category). The severity is medium because parameter changes affect 3D printer behavior and output, but changes are typically reversible by updating parameters again.
From the tool's definition Tool name is 'update_scad_parameter' with empty description. SCAD (OpenSCAD) is a parametric design language for 3D models. 'Update' indicates modification of design parameters that would alter 3D printer output.
Attacks that exploit this kind of access
update_scad_parameter. 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 update_scad_parameter: 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.
update_scad_parameter 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 update_scad_parameter 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 update_scad_parameter. 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.
update_scad_parameter 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 →