AI agents invoke upload_print to trigger actions in PrusaMCP. 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.
This tool uploads a G-code file and triggers a 3D print job on physical hardware (OctoPrint or PrusaConnect). It not only writes a file but also initiates an external operation (starting a print), making it Execute. Misuse could cause unintended prints, wasted material, or hardware damage. Severity is high due to physical-world consequences.
From the tool's definition Upload un fichier G-code vers OctoPrint ou PrusaConnect pour lancer l' [impression]
Attacks that exploit this kind of access
Upload un fichier G-code vers OctoPrint ou PrusaConnect pour lancer l. It is categorised as a Execute tool in the PrusaMCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Prusa MCP server in PolicyLayer and add a rule for upload_print: 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 PrusaMCP. Nothing to install.
upload_print 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 upload_print 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_print. 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_print is provided by the Prusa MCP server (noosbai/prusamcp). 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 →