AI agents call list_faces to retrieve information from Inventor without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries existing geometric data from a parametric model (Autodesk Inventor part) and returns structured information about faces. It has no side effects—it does not create, modify, delete, or execute operations. The blast radius of misuse is minimal; an AI agent calling this repeatedly or with invalid parameters would only retrieve data, causing no irreversible harm to the model.
From the tool's definition Tool name 'list_faces' and description indicate it retrieves and displays a 'compact face table' of geometric data from a 3D model body.
Attacks that exploit this kind of access
Compact face table of body 1: '[i] Plane A=90000 c=(0.0,225.0,12.5)' per line. It is categorised as a Read tool in the Inventor MCP Server, which means it retrieves data without modifying state.
Register the Inventor MCP server in PolicyLayer and add a rule for list_faces: 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 Inventor. Nothing to install.
list_faces 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_faces 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_faces. 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_faces is provided by the Inventor MCP server (neonglay/inventor-mcp). 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 →