AI agents call get_color_token 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 queries design system metadata to return color token values and descriptions. It performs a simple lookup/retrieval operation without modifying, creating, deleting, or executing any operations. No external side effects or irreversible actions are possible. This is a straightforward Read operation with minimal risk profile.
From the tool's definition Tool description uses '조회합니다' (retrieve/query) indicating a lookup operation on color tokens by name. The function name 'get_color_token' and sibling tools like 'get_token', 'list_color_tokens' confirm this is a retrieval operation with no side effects.
Attacks that exploit this kind of access
컬러 토큰 이름으로 정확한 값과 설명을 조회합니다 (예: Cool Gray/50). 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_color_token: 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_color_token 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_color_token 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_color_token. 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_color_token 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 →