AI agents call diff_design_versions to retrieve information from Kiln without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Diffing operations typically retrieve and display differences between versions without modifying data. No mutation, deletion, or execution of external processes is implied by the name. However, confidence is moderate due to the empty description. If this tool actually modifies designs or executes CAD operations (e.g., rendering or model processing), it could be reclassified as Execute.
From the tool's definition Tool name 'diff_design_versions' suggests comparing two design versions to show differences. The description is empty, providing no explicit confirmation of functionality.
Attacks that exploit this kind of access
diff_design_versions. It is categorised as a Read tool in the Kiln MCP Server, which means it retrieves data without modifying state.
Register the Kiln MCP server in PolicyLayer and add a rule for diff_design_versions: 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.
diff_design_versions is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the diff_design_versions 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 diff_design_versions. 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.
diff_design_versions 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 →