AI agents use save_design_version 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 or modifies design version records—a reversible write operation. It does not delete data (not Destructive), execute arbitrary code (not Execute), or involve financial transactions (not Financial). The medium severity reflects that corrupted or malicious design saves could affect print workflows, but the impact is limited to design data rather than physical printer control or permanent loss.
From the tool's definition Tool name 'save_design_version' indicates it writes/persists design data to storage. The empty description limits confidence, but context shows this is a 3D printing control server where design versioning is a core write operation.
Attacks that exploit this kind of access
save_design_version. 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_design_version: 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_design_version 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_design_version 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_design_version. 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_design_version 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 →