단일 라벨의 description + 샘플 자산 3개를 반환한다.
AI agents call describe_label to retrieve information from Assetcache 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 a label and shows examples. It queries and displays information without altering, deleting, or executing anything. No side effects on the asset store or system state. Classified as Read with low severity since retrieving asset metadata poses minimal risk even if misused by an agent.
From the tool's definition Tool returns description and sample assets (3개 = three) without modification. The verb pattern 'returns' (반환한다) and absence of any create/modify/delete operation indicates read-only retrieval.
Attacks that exploit this kind of access
단일 라벨의 description + 샘플 자산 3개를 반환한다. It is categorised as a Read tool in the Assetcache MCP Server, which means it retrieves data without modifying state.
Register the Assetcache MCP server in PolicyLayer and add a rule for describe_label: 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 Assetcache. Nothing to install.
describe_label 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 describe_label 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 describe_label. 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.
describe_label is provided by the Assetcache MCP server (v0o0v/assetcache-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 →