AI agents use product_duplicate to create or update resources in Voog — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Voog environment.
The tool creates a copy of an existing product in an ecommerce system. This is a Write operation because it creates new data reversibly (the duplicate can be edited or deleted). While it modifies system state, it does not irreversibly destroy data (Destructive), execute arbitrary code (Execute), or handle payments (Financial).
From the tool's definition Tool description states 'Duplicate a product (POST /admin/api/ecommerce/v1/products/' — the POST method and duplication action indicate data creation/modification without deletion or financial transaction.
Risk signalsAdmin/system-level operation
Attacks that exploit this kind of access
Duplicate a product (POST /admin/api/ecommerce/v1/products/. It is categorised as a Write tool in the Voog MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Voog MCP server in PolicyLayer and add a rule for product_duplicate: 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 Voog. Nothing to install.
product_duplicate 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 product_duplicate 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 product_duplicate. 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.
product_duplicate is provided by the Voog MCP server (runnel/voog-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 →