AI agents call list_categories to retrieve information from Vanam Erp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only retrieves/queries categorical metadata about inventory items with no ability to modify, delete, or execute operations. It has read-only semantics typical of data retrieval endpoints. The parent-child hierarchy traversal does not alter data. Blast radius is minimal as misuse would only expose organizational metadata already within the system.
From the tool's definition Tool name 'list_categories' and description indicate it "queries/조회(retrieves) the list of categories and parent-child hierarchy structure of inventory items" with no arguments required.
Attacks that exploit this kind of access
재고 품목의 카테고리(분류) 목록과 부모-자식 계층 구조를 조회한다. 인자가 필요 없다. 예:. It is categorised as a Read tool in the Vanam Erp MCP Server, which means it retrieves data without modifying state.
Register the Vanam Erp MCP server in PolicyLayer and add a rule for list_categories: 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 Vanam Erp. Nothing to install.
list_categories is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list_categories 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 list_categories. 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.
list_categories is provided by the Vanam Erp MCP server (leejunheon/vanam-erp-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 →