AI agents use create_product to create or update resources in Creem — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Creem environment.
This tool creates a new product record in a financial/commerce system, which is a Write operation (reversible creation/modification of data). The severity is high because products in commerce systems are foundational to revenue streams; misconfiguration or mass creation could disrupt business operations and customer experience.
From the tool's definition Tool name 'create_product' explicitly indicates a create operation. Description states 'Create a new product in Creem' which is a reversible data modification action.
Attacks that exploit this kind of access
Create a new product in Creem. Products can be one-time payments or recurring subscriptions. It is categorised as a Write tool in the Creem MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Creem MCP server in PolicyLayer and add a rule for create_product: 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 Creem. Nothing to install.
create_product 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_product 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_product. 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_product is provided by the Creem MCP server (selenium39/mcp-server-creem). 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 →