mcp-taiyi
Calculates Taiyi Shenshu (太乙神數) based on a given datetime and returns structured text and a board PNG image.
README
mcp-taiyi
기준 일시를 받아 태을신수(太乙神數) 국·산법을 계산해 구조화 텍스트와 포국 PNG를 반환하는 MCP 서버. (Python 런타임)
구조·네이밍·PNG·설치 규약은
STANDARD.md를 따른다(§6 Python 블록). mcp-qimen / mcp-liuren과 동일한 Python 패턴.
구성 / 계산
- 산법 엔진:
kintaiyi— 太乙 年計/月計/日計/時計/分計. - 천체력/유틸 의존:
sxtwl,ephem,numpy,cn2an(kintaiyi 내부 사용, 미선언이라 명시 설치). - 렌더:
Pillow— 산법 결과 그리드, 한자/한글 폰트. - 결정론적: 같은 입력 → 같은 국.
도구
get_taiyi
| 파라미터 | 타입 | 필수 | 기본 | 설명 |
|---|---|---|---|---|
datetime_str |
string YYYY-MM-DD HH:MM |
✅ | — | 기준 일시 |
mode |
year|month|day|hour|minute|ming |
day |
計 단위(年計~分計/命法) |
- mode 매핑:
year→年計,month→月計,day→日計,hour→時計,minute→分計. - ⚠️
ming(命法): kintaiyi 0.2.3은 命法을 직접 제공하지 않는다. 太乙命法이 출생 年計 반을 토대로 함에 따라 年計(ji_style 0)로 근사하며, 출력·PNG에 근사임을 명시한다. (집에서 함께 검증 예정)
출력 (둘 다 반환):
- 구조화 텍스트 — 局式·紀元·太歲·太乙落宮·文昌·始擊·主客算將參·定算·君臣民基 등
- 포국 PNG (1080×약760, 局式 배너 + 산법 그리드)
예제 출력: examples/taiyi_example.png (2024-02-10 14:30, 日計).
설치 (Python 3.10/3.11)
⚠️
sxtwl/ephem은 바이너리 휠이 필요하다. Windows에서는 Python 3.10 또는 3.11을 쓴다 (3.12+는 sxtwl 휠 부재 → 빌드 실패). Linux는 3.12도 manylinux 휠로 가능.
git clone https://github.com/molpass/mcp-taiyi.git
cd mcp-taiyi
python -m venv .venv && . .venv/bin/activate # Windows: .venv\Scripts\activate
pip install -r requirements.txt
예제 포국을 직접 생성해 보려면:
python examples/generate-example.py # examples/taiyi_example.png 재생성 + 전 mode 점검
폰트: 한자·한글 라벨을 위해 한글 가능 폰트가 필요하다. Windows는 Malgun Gothic 기본 탑재. Linux는 Noto CJK / Nanum 권장.
MCP 등록 (서버명 taiyi, STANDARD §6 Python)
{
"mcpServers": {
"taiyi": {
"command": "/abs/path/mcp-taiyi/.venv/bin/python",
"args": ["/abs/path/mcp-taiyi/server.py"]
}
}
}
Windows 예:
"command": "C:/Users/<you>/mcp-taiyi/.venv/Scripts/python.exe","args": ["C:/Users/<you>/mcp-taiyi/server.py"]
스킬
페어링 스킬: skill/taiyi.skill.md.
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.