recommend_buys
AI agents call recommend_buys to retrieve information from Kookmin Stock without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Despite the empty description lowering confidence slightly, the tool's name ('recommend_buys' not 'execute_buy' or 'place_order') and placement among exclusively data-retrieval tools strongly suggests it returns stock buy recommendations as read-only data. This is informational guidance, not financial execution. No capability to commit funds or irreversibly modify state is evident.
From the tool's definition Tool named 'recommend_buys' on a Korean stock market data server alongside read-only tools (get_fundamentals, get_market_overview, get_recent_news, get_stock_quote, get_top_gainers).
Attacks that exploit this kind of access
recommend_buys. It is categorised as a Read tool in the Kookmin Stock MCP Server, which means it retrieves data without modifying state.
Register the Kookmin Stock MCP server in PolicyLayer and add a rule for recommend_buys: 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 Kookmin Stock. Nothing to install.
recommend_buys 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 recommend_buys 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 recommend_buys. 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.
recommend_buys is provided by the Kookmin Stock MCP server (jooseunghyeon/kookmin-university-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 →