AI agents call list_3d_models to retrieve information from Meshy without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Even though list_3d_models only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
List your recently generated 3D models from Meshy. Returns task IDs, prompts, statuses, and download links for your most recent text-to-3D generations. It is categorised as a Read tool in the Meshy MCP Server, which means it retrieves data without modifying state.
Register the Meshy MCP server in PolicyLayer and add a rule for list_3d_models: 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 Meshy. Nothing to install.
list_3d_models 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 list_3d_models 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 list_3d_models. 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.
list_3d_models is provided by the Meshy MCP server (zyadhajaji/meshy-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.