AI agents call feedback_stats 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.
This tool queries and returns aggregated statistics about past 3D print jobs (success rates, etc.) without modifying, executing operations, or causing side effects. It is purely informational retrieval, fitting the Read category with low severity since misuse would only expose non-sensitive print history.
From the tool's definition Tool name 'feedback_stats' with description 'Affiche les statistiques de tes impressions : taux de réussite' (Display statistics of your prints: success rate) indicates retrieval and display of historical print performance data.
Attacks that exploit this kind of access
Affiche les statistiques de tes impressions : taux de réussite,. 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 feedback_stats: 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.
feedback_stats 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 feedback_stats 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 feedback_stats. 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.
feedback_stats 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 →