AI agents invoke set_temperature 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.
Setting temperature on a 3D printer triggers a physical external operation with real-world consequences — overheating can cause fires, equipment damage, or safety hazards. This falls under Execute (triggering external operations). The empty description lowers confidence, but the tool name combined with the 3D printer control context strongly implies this action.
From the tool's definition Tool name 'set_temperature' on a server described as 'AI agent control of 3D printers'. Description is empty and uninformative.
Attacks that exploit this kind of access
set_temperature. 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 set_temperature: 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.
set_temperature 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 set_temperature 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 set_temperature. 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.
set_temperature 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 →