저장된 검색 목록 (project_id 별, 최근 사용순).
AI agents call list_saved_searches 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 and queries saved search metadata without creating, modifying, or deleting data. It has no side effects and is purely informational, fitting the Read category. The severity is low because exposure of search history metadata poses minimal security risk compared to other asset operations on this server.
From the tool's definition Tool name 'list_saved_searches' and description indicating it lists saved searches organized by project_id in order of recent use. The verb 'list' and function of retrieving/enumerating existing data without modification.
Attacks that exploit this kind of access
저장된 검색 목록 (project_id 별, 최근 사용순). 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 list_saved_searches: 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.
list_saved_searches 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_saved_searches 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_saved_searches. 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_saved_searches 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 →