DART에 등록되어 있는 종목의 상장시장 정보를 제공합니다. Y(유가), K(코스닥), N(코넥스), E(기타)
AI agents call get_market_type to retrieve information from Korea Stock without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a pure query operation that retrieves and displays static stock market classification data. It has no side effects, cannot modify data, cannot execute commands, and cannot affect financial transactions. The blast radius of misuse is minimal—an agent could only retrieve classification metadata about Korean stocks.
From the tool's definition Tool provides market type information (유가/Y, 코스닥/K, 코넥스/N, 기타/E) for registered securities. The description indicates data retrieval only ('정보를 제공합니다' = 'provides information').
Attacks that exploit this kind of access
DART에 등록되어 있는 종목의 상장시장 정보를 제공합니다. Y(유가), K(코스닥), N(코넥스), E(기타). It is categorised as a Read tool in the Korea Stock MCP Server, which means it retrieves data without modifying state.
Register the Korea Stock MCP server in PolicyLayer and add a rule for get_market_type: 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 Korea Stock. Nothing to install.
get_market_type 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_market_type 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_market_type. 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_market_type is provided by the Korea Stock MCP server (korea-stock-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 →