AI agents call career_guidance 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 generates astrological interpretations and career recommendations based on existing chart data. It retrieves and analyzes information to produce guidance, with no side effects on data storage, external systems, or financial transactions. This is a pure Read operation: querying astrological data to provide decision-support output.
From the tool's definition Tool name 'career_guidance' combined with description '职业发展指导和决策支持' (career development guidance and decision support) indicates the tool provides interpretive analysis and advice based on astrological charts.
Documented attack patterns abuse exactly the kind of access career_guidance 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 career_guidance:
{
"version": "1",
"default": "deny",
"tools": {
"career_guidance": {}
}
}career_guidance 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.
职业发展指导和决策支持. 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 career_guidance: 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.
career_guidance 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 career_guidance 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 career_guidance. 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.
career_guidance 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.