find_company_by_name
AI agents call find_company_by_name 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 tool queries a financial disclosure database to locate companies by name. It retrieves read-only data with no side effects, matching the 'Read' category. Severity is low because a name lookup on public corporate data poses minimal risk even if misused by an AI agent. The confidence is high despite the empty description because the tool name and server context strongly indicate a simple lookup function.
From the tool's definition Tool name 'find_company_by_name' indicates a search/lookup operation. Server description confirms it retrieves corporate information from DART without modification.
Attacks that exploit this kind of access
find_company_by_name. 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 find_company_by_name: 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.
find_company_by_name 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_by_name 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_by_name. 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_by_name 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 →