This record as markdown: /tools/kiln/send-gcode.md
What send_gcode does on Kiln
AI agents invoke send_gcode 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.
Why send_gcode is rated High
Sending GCode to a 3D printer executes arbitrary machine instructions that control physical actuators. Misuse could cause hardware damage (overheating, motor crashes), fire hazards, or destruction of prints and equipment. The description is empty, but the tool name in context of a 3D printer control server makes the function clear.
From the tool's definition Tool name 'send_gcode' on a server described as 'AI agent control of 3D printers'. GCode is a command language that directly controls physical hardware (movement, temperature, extrusion, fans, etc.).
Attacks that exploit this kind of access
The rule that runs send_gcode safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Kiln, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For send_gcode, this is the rule to start with:
send_gcode stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Kiln, apply this rule, and every send_gcode call is checked against it from then on.
Questions about send_gcode
send_gcode is a execute tool on the Kiln MCP server. 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 send_gcode: 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.
send_gcode 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 send_gcode 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 send_gcode. 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.
send_gcode 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.
More on Kiln, and thousands of servers like it.
This server
Across the catalogue