find_company
AI agents call find_company to retrieve information from Koreafilings without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name suggests a query/retrieval function for locating company records. Without a description, confidence is moderate, but the pattern of sibling tools (get_pricing, get_disclosure_summary, list_recent_filings) all being read operations suggests this follows the same pattern. No evidence of side effects, financial transactions, code execution, or destructive operations.
From the tool's definition Tool name 'find_company' indicates a search or lookup operation. No description provided, but based on naming conventions and context of a DART disclosure server, this appears to retrieve company information without modifying data.
Attacks that exploit this kind of access
find_company. It is categorised as a Read tool in the Koreafilings MCP Server, which means it retrieves data without modifying state.
Register the Koreafilings MCP server in PolicyLayer and add a rule for find_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 Koreafilings. Nothing to install.
find_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 find_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 find_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.
find_company is provided by the Koreafilings MCP server (oldtemple91/korea-filings-api). 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 →