AI agents call analyze_mesh 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 and computes geometric data from 3D model files (STL/3MF format) without creating, modifying, executing external operations, or deleting data. This is purely informational analysis, fitting the Read category with low severity since unauthorized mesh analysis poses minimal risk.
From the tool's definition Tool name is 'analyze_mesh' and description indicates it analyzes a file and 'returns: dimensions, volume, surface' - these are read-only queries of geometric properties with no side effects or modifications.
Attacks that exploit this kind of access
Analyse un fichier STL ou 3MF et retourne : dimensions, volume, surface,. 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 analyze_mesh: 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.
analyze_mesh 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 analyze_mesh 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 analyze_mesh. 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.
analyze_mesh 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 →