AI agents use suppress_feature to create or update resources in Inventor — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Inventor environment.
Suppressing/unsuppressing features modifies the parametric model state and affects the resulting 3D geometry without irreversibly destroying data. This is a reversible Write operation rather than Destructive (which would be permanent deletion). While it changes the design, the operation can be undone by toggling the suppress state.
From the tool's definition Tool description states "Suppress or unsuppress features (hide without deleting)" — this modifies the state of design features in a reversible manner without permanent deletion.
Attacks that exploit this kind of access
Suppress or unsuppress features (hide without deleting). Use list_features() to find indices. It is categorised as a Write tool in the Inventor MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Inventor MCP server in PolicyLayer and add a rule for suppress_feature: 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.
suppress_feature is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the suppress_feature 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 suppress_feature. 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.
suppress_feature 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 →