紫微斗数 MCP 服务器 (MCPIztro)
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_current_timeB | 获取当前系统时间，返回详细的时间信息 |
| calculate_ziweiA | 计算指定生辰的紫微斗数星盘，返回完整的星盘数据（包含十二宫、星耀、亮度等）。支持经纬度参数，将时间转换为真太阳时进行更精确的计算 |
| get_horoscopeC | 获取指定生辰在特定时间的运限信息（大限、流年等）。支持经纬度参数，将时间转换为真太阳时进行更精确的计算 |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
The tools have mostly distinct purposes: calculate_ziwei for natal charts, get_horoscope for time-based horoscopes, and get_current_time for system time. However, get_current_time might be confused as a helper for the other tools rather than a standalone feature, creating minor ambiguity in the set's scope.
All tool names follow a consistent verb_noun pattern with snake_case (calculate_ziwei, get_current_time, get_horoscope). The verbs 'calculate' and 'get' are clear and appropriate for their functions, making the naming highly predictable.
With only 3 tools, the set feels thin for a Zi Wei Dou Shu server, as it lacks operations like updating charts, comparing charts, or accessing historical data. While the core functions are present, the low count may limit agent workflows in this domain.
The server covers basic natal chart calculation and horoscope retrieval, but there are notable gaps: no update or delete operations for saved charts, no chart comparison tools, and no methods for interpreting or analyzing results beyond raw data. This could lead to dead ends in complex agent tasks.