AI agents invoke slice_prusaslicer 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 executes an external CLI application (PrusaSlicer) to slice 3D model files and produce G-code. Running external CLI tools constitutes Execute category. Severity is high because it invokes arbitrary external processes, consumes system resources, and generates files that could be sent to a 3D printer, potentially causing physical-world effects.
From the tool's definition 'Slice un fichier STL/3MF avec PrusaSlicer CLI' — invokes PrusaSlicer CLI (an external program) to process files and generate G-code output
Attacks that exploit this kind of access
Slice un fichier STL/3MF avec PrusaSlicer CLI et retourne le G-code + statistiques. 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 slice_prusaslicer: 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.
slice_prusaslicer 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 slice_prusaslicer 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 slice_prusaslicer. 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.
slice_prusaslicer 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 →