AI agents use fillet 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.
The fillet tool modifies the part design by adding geometric features to edges. This is a Write-class operation because it creates or modifies data (the solid body geometry) in a reversible manner. Severity is medium because misuse could alter the design in unintended ways, affecting model validity or aesthetics, but the impact is limited to a single 3D model's geometry and can be undone.
From the tool's definition Tool performs 'Add fillet (rounded edge) to edges of the solid body', which modifies the 3D model geometry but does not delete or destroy data, nor does it execute arbitrary code. The operation is reversible—fillets can be removed or adjusted.
Attacks that exploit this kind of access
Add fillet (rounded edge) to edges of the solid body. Radius in mm. 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 fillet: 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.
fillet 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 fillet 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 fillet. 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.
fillet 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 →