AI agents call compare_financials 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 compares already-published financial disclosure data from DART (a Korean corporate disclosure database). Comparison is an analytical operation that does not create, modify, delete, or execute anything. The blast radius of misuse is minimal—an agent could only access publicly available corporate financial data, which is the intended use case. This is a straightforward Read operation.
From the tool's definition Tool name 'compare_financials' and description 'Compare financial data across multiple Korean companies' indicate data retrieval and comparison operations. No mention of modifications, deletions, code execution, or financial transactions.
Attacks that exploit this kind of access
Compare financial data across multiple Korean companies. 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 compare_financials: 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.
compare_financials 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 compare_financials 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 compare_financials. 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.
compare_financials 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 →