AI agents call recommend_short_drama to retrieve information from Xunjuzhou without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool queries and returns recommendations from the server's drama database based on user preferences. It performs no creation, modification, deletion, code execution, or financial transactions. The server is explicitly read-only, and all sibling tools (find_similar_short_drama, get_hot_short_drama, get_short_drama_detail, search_short_drama) are clearly query/retrieval operations.
From the tool's definition Server is explicitly described as 'read-only' and this tool 'recommend[s] short dramas' based on preferences, which is a retrieval and recommendation operation with no side effects.
Attacks that exploit this kind of access
Recommend short dramas from a plain-language preference without calling an LLM. It is categorised as a Read tool in the Xunjuzhou MCP Server, which means it retrieves data without modifying state.
Register the Xunjuzhou MCP server in PolicyLayer and add a rule for recommend_short_drama: 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 Xunjuzhou. Nothing to install.
recommend_short_drama 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 recommend_short_drama 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 recommend_short_drama. 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.
recommend_short_drama is provided by the Xunjuzhou MCP server (wildmin/xunjuzhou-mcp-server). 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 →