AI agents use compose_assembly_parts 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.
Based on the name alone, 'compose_assembly_parts' likely creates or modifies a 3D model assembly by combining parts together — a Write operation. Confidence is low due to the empty description. It could be Execute if it triggers a physical printer operation, but Write is the most reasonable inference from the name in context of sibling tools like 'add_assembly_part' and 'add_assembly_interface'.
From the tool's definition Tool name 'compose_assembly_parts' suggests combining or creating an assembly from parts; description is empty and uninformative.
Attacks that exploit this kind of access
compose_assembly_parts. 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 compose_assembly_parts: 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.
compose_assembly_parts 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 compose_assembly_parts 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 compose_assembly_parts. 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.
compose_assembly_parts 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 →