AI agents call get_financial_summary to retrieve information from Opendart without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and aggregates existing financial data from the Korean DART disclosure system. It has no capability to modify, delete, execute code, or commit financial transactions. The read-only nature is evident from the verb 'Get' and the fact it accesses a public disclosure database. Even if sensitive financial data is returned, the risk is informational only with no side effects from tool execution.
From the tool's definition Tool is named 'get_financial_summary' and described as 'Get key financial data for a Korean company' — purely a retrieval operation with no modification or execution capabilities.
Attacks that exploit this kind of access
Get key financial data for a Korean company. It is categorised as a Read tool in the Opendart MCP Server, which means it retrieves data without modifying state.
Register the Opendart MCP server in PolicyLayer and add a rule for get_financial_summary: 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 Opendart. Nothing to install.
get_financial_summary 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_financial_summary 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_financial_summary. 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_financial_summary is provided by the Opendart MCP server (songhyojun0228/opendart-mcp-server). 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 →