AI agents use create_part 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.
This tool creates a new part document, which is a reversible write operation. It does not execute code, delete data, or move financial resources. However, the severity is medium rather than low because in an automated context, unchecked document creation could consume resources or clutter the workspace, and creation of malformed or unwanted parts could require manual cleanup.
From the tool's definition Tool name 'create_part' and description 'Create a new empty part document' indicate creation of a new document/object without deletion or execution of external operations.
Attacks that exploit this kind of access
Create a new empty part document. 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 create_part: 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.
create_part 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 create_part 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 create_part. 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.
create_part 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 →