获取酒店搜索标签元数据（AI Cache），包含可用标签列表。
AI agents call getHotelSearchTags to retrieve information from RollingGo-Hotel-MCP 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 static metadata (available tag lists) for hotel search functionality. It has no side effects, does not modify data, and presents minimal security risk. It fits the 'Read' category as a simple data retrieval operation used to support search capabilities.
From the tool's definition Tool name 'getHotelSearchTags' and description indicate retrieval of metadata about available hotel search tags. The phrase '获取酒店搜索标签元数据' translates to 'retrieve hotel search tag metadata'.
Attacks that exploit this kind of access
获取酒店搜索标签元数据（AI Cache），包含可用标签列表。. It is categorised as a Read tool in the RollingGo-Hotel-MCP MCP Server, which means it retrieves data without modifying state.
Register the RollingGo-Hotel- MCP server in PolicyLayer and add a rule for getHotelSearchTags: 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 RollingGo-Hotel-MCP. Nothing to install.
getHotelSearchTags 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 getHotelSearchTags 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 getHotelSearchTags. 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.
getHotelSearchTags is provided by the RollingGo-Hotel- MCP server (rollinggo-ai/rollinggo-hotel-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 →