Create a new category
AI agents use vtex_create_category to create or update resources in MCP VTEX Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP VTEX Server environment.
This tool creates new data (a category) in the VTEX e-commerce platform, which is a Write operation. While reversible, creating categories can affect product organization, navigation, and customer experience, warranting medium severity. The confidence is high because the intent is explicit in both name and description.
From the tool's definition Tool name is 'vtex_create_category' and description states 'Create a new category'. The action is reversible (categories can be modified or deleted later).
Attacks that exploit this kind of access
Create a new category. It is categorised as a Write tool in the MCP VTEX Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP VTEX Server MCP server in PolicyLayer and add a rule for vtex_create_category: 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 VTEX Server. Nothing to install.
vtex_create_category 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 vtex_create_category 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 vtex_create_category. 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.
vtex_create_category is provided by the MCP VTEX Server MCP server (leosepulveda/mcp-vtex). 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 →