AI agents call get_component_code_usage to retrieve information from GDS MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves design system metadata (component code examples and usage patterns) without creating, modifying, executing, or destroying anything. It is purely informational and safe for AI agents to call. Low severity due to read-only nature and limited blast radius.
From the tool's definition Tool description states it 'returns actual code usage' of a component, providing import statements, props, and patterns—all retrieval operations with no modification or execution capability.
Attacks that exploit this kind of access
특정 컴포넌트의 실제 코드 사용법만 반환합니다. import, props 기반 flat pattern, 조립형 compound pattern 예시가 필요할 때 사용하세요. It is categorised as a Read tool in the GDS MCP MCP Server, which means it retrieves data without modifying state.
Register the GDS MCP server in PolicyLayer and add a rule for get_component_code_usage: 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 GDS MCP. Nothing to install.
get_component_code_usage 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_component_code_usage 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_component_code_usage. 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_component_code_usage is provided by the GDS MCP server (supin-kim-ilevit-com/gds-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 →