AI agents call get_current_model to retrieve information from PrusaMCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves metadata about the currently active file in PrusaSlicer by querying window state. It performs no modifications, executions, or destructive operations. This is a straightforward Read operation with minimal risk—even if an AI agent misuses it, the worst outcome is learning which file is open, which is low-sensitivity information.
From the tool's definition Tool description states it 'Détecte le fichier actuellement ouvert' (detects the currently open file) by 'lisant le titre de la fenêtre' (reading the window title). This is a passive information retrieval operation with no side effects.
Attacks that exploit this kind of access
Détecte le fichier actuellement ouvert dans PrusaSlicer en lisant le titre de la fenêtre. It is categorised as a Read tool in the PrusaMCP MCP Server, which means it retrieves data without modifying state.
Register the Prusa MCP server in PolicyLayer and add a rule for get_current_model: 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.
get_current_model is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_current_model 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 get_current_model. 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.
get_current_model 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 →