AI agents call list_components 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 metadata about available components from a design system without creating, modifying, deleting, or executing anything. It is a read-only informational query, similar to other Read tools on the same server (list_tokens, list_guidelines, list_color_tokens). The blast radius of misuse is minimal—an AI could only waste API quota or receive irrelevant design information.
From the tool's definition Tool name 'list_components' and description indicate it 'returns a list of components defined in Levit design system' - a simple query operation with no modification or execution.
Attacks that exploit this kind of access
Levit 디자인 시스템에 정의된 컴포넌트 목록을 반환합니다. 특정 컴포넌트 이름을 모를 때 먼저 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 list_components: 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.
list_components 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 list_components 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 list_components. 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.
list_components 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 →