코스피 공포탐욕지수 (인덱서고 idxDetail=24501, 일간) — 현재값 + 영업일 시계열.
AI agents call get_kospi_fear_greed to retrieve information from Yummy Research without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool merely queries and returns market sentiment index data. It performs no state changes, does not execute operations with variable effects, does not delete data, and does not involve financial transactions. It is a straightforward read operation consistent with the server's purpose of exposing macro/market statistics.
From the tool's definition Tool name includes 'get_' prefix and description indicates it retrieves 'current value + business day time series' data from the KOSPI Fear & Greed Index (idxDetail=24501).
Attacks that exploit this kind of access
코스피 공포탐욕지수 (인덱서고 idxDetail=24501, 일간) — 현재값 + 영업일 시계열. It is categorised as a Read tool in the Yummy Research MCP Server, which means it retrieves data without modifying state.
Register the Yummy Research MCP server in PolicyLayer and add a rule for get_kospi_fear_greed: 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 Yummy Research. Nothing to install.
get_kospi_fear_greed 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_kospi_fear_greed 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_kospi_fear_greed. 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_kospi_fear_greed is provided by the Yummy Research MCP server (yeom/yummy-research-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 →