AI agents call get_portfolio_summary 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 data retrieval and analysis operations only. It queries existing portfolio information to provide summary metrics and performance analysis. No data is created, modified, deleted, or financial transactions are executed. This is a standard read operation with minimal risk if misused by an AI agent.
From the tool's definition get_portfolio_summary retrieves and analyzes portfolio overview data including total valuation (총평가금액), total profit/loss (총손익), and return rate (수익률) without modifying or executing any transactions.
Attacks that exploit this kind of access
총평가금액, 총손익, 수익률 등 포트폴리오 전체 현황을 분석합니다. 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 get_portfolio_summary: 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.
get_portfolio_summary 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 get_portfolio_summary 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 get_portfolio_summary. 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.
get_portfolio_summary 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 →