사회적책임투자(SRI) 채권 정보를 조회합니다.
AI agents call get_sri_bond_info to retrieve information from OpenKRX MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a data retrieval tool that queries Korean Exchange SRI (Socially Responsible Investment) bond information. It follows the Read pattern consistent with sibling tools (get_bond_index_daily, get_etf_daily, etc.) that all retrieve market data without side effects. Reading financial market data poses minimal risk regardless of the data domain.
From the tool's definition Tool name 'get_sri_bond_info' and description '사회적책임투자(SRI) 채권 정보를 조회합니다' (retrieves SRI bond information). The verb '조회' means 'to query/retrieve'. No modifications, deletions, executions, or financial transactions are performed.
Attacks that exploit this kind of access
사회적책임투자(SRI) 채권 정보를 조회합니다. It is categorised as a Read tool in the OpenKRX MCP Server MCP Server, which means it retrieves data without modifying state.
Register the OpenKRX MCP Server MCP server in PolicyLayer and add a rule for get_sri_bond_info: 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 OpenKRX MCP Server. Nothing to install.
get_sri_bond_info 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_sri_bond_info 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_sri_bond_info. 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_sri_bond_info is provided by the OpenKRX MCP Server MCP server (realyoungk/openkrx-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 →