Create a new product with smart ai generated description if missing
AI agents use add_product_smart to create or update resources in MCP E-commerce Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP E-commerce Server environment.
This tool creates new product records in the e-commerce database, which is a reversible Write operation. While it involves AI-generated content, the core action is persisting new data to the SQLite backend.
From the tool's definition Tool name 'add_product' and description 'Create a new product' indicate data creation. The 'smart ai generated description if missing' aspect adds a Write operation with conditional logic, not Read, Execute, or Destructive behavior.
Attacks that exploit this kind of access
Create a new product with smart ai generated description if missing. It is categorised as a Write tool in the MCP E-commerce Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP E-commerce Server MCP server in PolicyLayer and add a rule for add_product_smart: 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 MCP E-commerce Server. Nothing to install.
add_product_smart 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 add_product_smart 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 add_product_smart. 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.
add_product_smart is provided by the MCP E-commerce Server MCP server (vanushya/mcp-example). 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 →