Search DART disclosures with various filters. Returns a list of disclosure reports with company name, report title, filing date, and receipt number. Args: - corp_code (optional): 8-digit company code to filter by - bgn_de (optional): Start date (YYYYMMDD) - end_de (optional): End date (YYYYMMDD) ...
AI agents call opendart_search_disclosure to retrieve information from OpenDART 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 pure data retrieval tool that queries public Korean financial disclosure records. It has no side effects, does not modify data, and does not execute code or trigger external operations. The filtering arguments are standard query parameters. Access to public financial filing data poses minimal risk even if misused by an AI agent, making severity low.
From the tool's definition Tool description states it 'Search[es] DART disclosures' and 'Returns a list of disclosure reports with company name, report title, filing date, and receipt number.' No modification, deletion, or execution capability is described.
Attacks that exploit this kind of access
Search DART disclosures with various filters. Returns a list of disclosure reports with company name, report title, filing date, and receipt number. Args: - corp_code (optional): 8-digit company code to filter by - bgn_de (optional): Start date (YYYYMMDD) - end_de (optional): End date (YYYYMMDD) - last_reprt_at (optional):. It is categorised as a Read tool in the OpenDART MCP Server MCP Server, which means it retrieves data without modifying state.
Register the OpenDART MCP Server MCP server in PolicyLayer and add a rule for opendart_search_disclosure: 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 MCP Server. Nothing to install.
opendart_search_disclosure 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 opendart_search_disclosure 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 opendart_search_disclosure. 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.
opendart_search_disclosure is provided by the OpenDART MCP Server MCP server (procpalee/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 →