get_debt_information_summary_details
AI agents call get_debt_information_summary_details to retrieve information from OpenDart-MCP 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 operation with no side effects—it queries and returns existing financial disclosure data. The medium severity reflects that detailed debt information about companies could be sensitive competitive/financial information, but retrieval alone does not modify or delete data.
From the tool's definition Tool name 'get_debt_information_summary_details' indicates retrieval of debt summary data from DART system. Server description confirms it enables retrieval of 'debt summaries' for Korean companies.
Attacks that exploit this kind of access
get_debt_information_summary_details. It is categorised as a Read tool in the OpenDart-MCP MCP Server, which means it retrieves data without modifying state.
Register the OpenDart- MCP server in PolicyLayer and add a rule for get_debt_information_summary_details: 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. Nothing to install.
get_debt_information_summary_details 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_debt_information_summary_details 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_debt_information_summary_details. 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_debt_information_summary_details is provided by the OpenDart- MCP server (keonho-kim/opendart-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 →