AI agents use save_decoration 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.
With an empty description, confidence is reduced. However, 'save' typically implies Write operations (creation or modification of data). In a 3D printer context, this likely modifies design or decoration settings reversibly. Without evidence of destructive intent or side effects, Write is the most appropriate category.
From the tool's definition Tool name 'save_decoration' and server context (3D printer control) suggest the tool creates or modifies decorative parameters or settings for 3D printer designs. The 'save' verb indicates data persistence.
Attacks that exploit this kind of access
save_decoration. 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 save_decoration: 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.
save_decoration 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 save_decoration 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 save_decoration. 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.
save_decoration 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 →