AI agents call search_company 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 is classified as Read because it only queries and retrieves publicly available corporate disclosure data without any side effects. The blast radius is minimal—returning incorrect or malicious search results might mislead users but cannot modify financial records, execute operations, or cause irreversible damage.
From the tool's definition The tool 'search_company' with description 'Search for a Korean company and get basic corporate info' performs a search and retrieval operation. No modification, deletion, or execution of external systems is indicated.
Attacks that exploit this kind of access
Search for a Korean company and get basic corporate info. 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 search_company: 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.
search_company 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 search_company 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 search_company. 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.
search_company 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 →