AI agents use create_assembly 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.
This tool creates a new assembly object, which is a write operation that modifies the 3D design/model state reversibly. It does not execute print commands, delete data, move money, or trigger external hardware actions. The blast radius is low: creating an empty assembly has minimal side effects and is easily undone by deletion or model reset.
From the tool's definition Tool name is 'create_assembly' and description states 'Create a new empty assembly' — a creation action that adds new data structure to the system.
Attacks that exploit this kind of access
Create a new empty assembly. 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 create_assembly: 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.
create_assembly 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 create_assembly 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 create_assembly. 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.
create_assembly 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 →