자연어 쿼리에 어울리는 팩 후보를 정렬한다 (사용자에게 팩 선택권 제공).
AI agents call suggest_packs 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 queries and ranks packs based on user input but does not create, modify, delete, execute code, or move money. It is a read-only operation that returns recommendations to help users choose among existing asset packs. The low severity reflects minimal risk if misused by an AI agent—it can only suggest packs from the existing inventory.
From the tool's definition The tool description indicates it 'sorts pack candidates matching natural language queries' and 'provides users with pack selection options.' The verb 'suggest' and the phrase 'provide selection options' confirm this is a retrieval/recommendation tool with no…
Attacks that exploit this kind of access
자연어 쿼리에 어울리는 팩 후보를 정렬한다 (사용자에게 팩 선택권 제공). 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 suggest_packs: 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.
suggest_packs 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 suggest_packs 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 suggest_packs. 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.
suggest_packs 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 →