AI agents call find_token_by_value 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 is a query/lookup operation against design system metadata. It retrieves information about which color token corresponds to a provided hex value, with no side effects or ability to modify, delete, or execute code. This falls cleanly into the Read category with low severity, as misuse poses minimal risk—an agent could only retrieve token information that is already documented in the design system.
From the tool's definition Tool performs a reverse lookup of hex color values to identify corresponding color tokens. The description indicates it 'searches' (역검색) and 'checks' which token a given hex value matches.
Attacks that exploit this kind of access
hex 색상 값으로 어떤 컬러 토큰인지 역검색합니다. 디자인 시안이나 코드에서 발견한 hex가 어떤 토큰에 해당하는지 확인할 때 사용하세요. #FFF / #FFFFFF / 대소문자 차이를 자동으로 흡수합니다. 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 find_token_by_value: 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.
find_token_by_value 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_token_by_value 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_token_by_value. 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_token_by_value 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 →