AI agents call getChineseCalendar to retrieve information from Bazi MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a pure data retrieval operation. It queries and returns Chinese calendar information (lunar dates, auspicious times, etc.) for a specified date, defaulting to today. There are no side effects, no data modification, no code execution, and no destructive operations. This falls squarely into the Read category as a lookup/query tool with minimal risk even if misused by an AI agent.
From the tool's definition Tool name 'getChineseCalendar' and description indicate it retrieves/queries Chinese calendar (黄历) information for a given date. The description states it 'gets' (获取) lunar calendar information with no mention of modification, deletion, or state changes.
Attacks that exploit this kind of access
获取指定公历时间（默认今天）的黄历信息。. It is categorised as a Read tool in the Bazi MCP MCP Server, which means it retrieves data without modifying state.
Register the Bazi MCP server in PolicyLayer and add a rule for getChineseCalendar: 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 Bazi MCP. Nothing to install.
getChineseCalendar 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 getChineseCalendar 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 getChineseCalendar. 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.
getChineseCalendar is provided by the Bazi MCP server (shuangzixing1976/bazi-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 →