AI agents call health_analysis to retrieve information from Ziwei without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and analyzes astrological data to provide health and wellness insights. It performs data interpretation and reporting without side effects, aligning with the Read category. The severity is low because misuse would only produce inaccurate astrological advice with no structural, operational, or financial impact.
From the tool's definition Tool name 'health_analysis' with description '健康分析和养生建议' (health analysis and wellness advice). The description indicates analysis and advice generation based on astrological charts, with no capability to modify, delete, execute external systems, or affect…
Documented attack patterns abuse exactly the kind of access health_analysis gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Ziwei, and nothing reaches the server without passing your rules. This is the rule we recommend for health_analysis:
{
"version": "1",
"default": "deny",
"tools": {
"health_analysis": {}
}
}health_analysis is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
健康分析和养生建议. It is categorised as a Read tool in the Ziwei MCP Server, which means it retrieves data without modifying state.
Register the Ziwei MCP server in PolicyLayer and add a rule for health_analysis: 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 Ziwei. Nothing to install.
health_analysis 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 health_analysis 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 health_analysis. 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.
health_analysis is provided by the Ziwei MCP server (siwuxue/ziwei-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Ziwei, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
12 Ziwei tools catalogued and risk-classified — across an index of 43,000+ MCP servers.