AI agents call get_feedback_loop_status 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.
This tool retrieves historical data about feedback loops for a generated 3D model. It performs a read-only query without creating, modifying, deleting, or executing actions on the printer or its output. Even in the context of AI-controlled 3D printers, reading feedback history poses minimal risk—it cannot damage hardware, corrupt designs, or cause financial harm.
From the tool's definition Tool name contains 'get' and description states 'Get the feedback loop history' — a pure retrieval operation with no side effects or modifications to printer state or generated models.
Attacks that exploit this kind of access
Get the feedback loop history for a generated model. 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 get_feedback_loop_status: 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.
get_feedback_loop_status 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 get_feedback_loop_status 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 get_feedback_loop_status. 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.
get_feedback_loop_status 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 →