AI agents use upload_file_confirm to create or update resources in Kiln — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Kiln environment.
The tool appears to confirm or finalize file uploads to 3D printer hardware. This is a Write operation (reversible creation/modification of data on the printer). Severity is medium because a malicious file upload could cause printer malfunction, hardware damage, or safety issues, but the effect is bounded to a single device rather than cascading financial or data destruction.
From the tool's definition Tool name 'upload_file_confirm' suggests confirmation of file uploads to 3D printer systems (OctoPrint, Moonraker, Bambu, Prusa, Elegoo). The 'upload_file' action pattern indicates writing/storing files to printer firmware or control systems.
Attacks that exploit this kind of access
upload_file_confirm. It is categorised as a Write tool in the Kiln MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Kiln MCP server in PolicyLayer and add a rule for upload_file_confirm: 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.
upload_file_confirm is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the upload_file_confirm 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 upload_file_confirm. 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.
upload_file_confirm 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 →