AI agents call get_account_balance 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 is a Read operation—it queries and retrieves account balance and portfolio data with no side effects. Severity is medium rather than low because the data retrieved is sensitive financial information (account holdings, balances) that could be misused if exposed, but the tool itself performs no destructive or financial transaction. It does not move money, execute trades, or modify data.
From the tool's definition Tool description translates to 'inquire account balance including list of held stocks, current price, purchase price, purchase amount, etc.' The tool retrieves account information without modifying, deleting, or moving money.
Attacks that exploit this kind of access
보유 주식 목록, 현재가, 매입가, 매입금액 등 계좌 잔고를 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 get_account_balance: 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_account_balance 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_account_balance 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_account_balance. 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_account_balance 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 →