AI agents call get_company_info to retrieve information from Dart without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries publicly available company information from Korea's official DART electronic disclosure system. The operation has no side effects—it retrieves existing data without creating, modifying, deleting, executing code, or moving money. The blast radius of misuse is minimal, as the data is public and read-only access poses no security risk.
From the tool's definition Tool retrieves company profile information (name, CEO, registration numbers) with no modification capability. The verb 'Get' and the read-only nature of querying a public disclosure system indicate a retrieval operation.
Attacks that exploit this kind of access
Get company profile from DART: name, CEO, registration numbers,. It is categorised as a Read tool in the Dart MCP Server, which means it retrieves data without modifying state.
Register the Dart MCP server in PolicyLayer and add a rule for get_company_info: 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 Dart. Nothing to install.
get_company_info 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_company_info 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_company_info. 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_company_info is provided by the Dart MCP server (vertical-mcp/dart-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 →