AI agents invoke clear_emergency_stop to trigger actions in Kiln. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Clearing an emergency stop on a physical 3D printer re-enables machine motion and heating elements that were halted for safety reasons. This is an Execute-class action with critical severity because misuse could bypass a safety interlock, potentially causing physical harm, fire, or equipment damage.
From the tool's definition Tool name: 'clear_emergency_stop' — implies resetting or clearing an emergency stop state on a 3D printer
Attacks that exploit this kind of access
clear_emergency_stop. It is categorised as a Execute tool in the Kiln MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Kiln MCP server in PolicyLayer and add a rule for clear_emergency_stop: 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.
clear_emergency_stop is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the clear_emergency_stop 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 clear_emergency_stop. 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.
clear_emergency_stop 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.
clear_emergency_stop is one line of Kiln's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →