AI agents call search_stock to retrieve information from Kiwoom without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only lookup of publicly available stock metadata. It does not modify data, execute trades, delete information, or involve financial transactions. The information retrieved (stock name, market classification, industry, listing date) are static reference data. This is the least severe category with minimal blast radius for misuse by an AI agent.
From the tool's definition Tool description states it 'retrieves stock basic information' (종목 기본 정보를 조회합니다) including stock name, market type, industry, and listing date by stock code. The verb '조회' (query/lookup) indicates data retrieval without modification.
Attacks that exploit this kind of access
종목코드로 종목명, 시장구분, 업종, 상장일 등 종목 기본 정보를 조회합니다. It is categorised as a Read tool in the Kiwoom MCP Server, which means it retrieves data without modifying state.
Register the Kiwoom MCP server in PolicyLayer and add a rule for search_stock: 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 Kiwoom. Nothing to install.
search_stock 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 search_stock 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 search_stock. 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.
search_stock is provided by the Kiwoom MCP server (kwonsw812/kiwoom-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 →