AI agents call find_face 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.
Despite the empty description, the semantics of 'find' followed by a geometric element (face) strongly indicate this is a query operation that retrieves or identifies existing geometry without modification. The tool name pattern matches typical read-only geometry selection/inspection tools in CAD systems.
From the tool's definition Tool name 'find_face' suggests retrieval or identification of geometric elements in a 3D model. The empty description prevents confirmation, but context from sibling tools (which include destructive operations like delete_feature, chamfer, and create…
Attacks that exploit this kind of access
find_face. 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 find_face: 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.
find_face 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 find_face 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 find_face. 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.
find_face 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 →