This server performs Da Liu Ren (大六壬) divination, computing celestial and earthly plates and returning both structured text and a PNG image.
Inputs:
Provide a datetime string (YYYY-MM-DD HH:MM) for automatic Chinese calendar conversion via lunar_python.
Or manually supply Ganzhi (干支) fields — solar term (jieqi), lunar month (cmonth), day Ganzhi (dayGanzhi), and hour Ganzhi (hourGanzhi) — to bypass calendar conversion.
Outputs:
Structured text including:
三傳 (Three Transmissions) — branch, heavenly general, six relations, and hidden stem
四課 (Four Courses)
天地盤 (Heaven-Earth Disk arrangement)
格局 (Chart Patterns/Configurations)
神煞 (Spirit Deities, e.g. 日馬)
A 1080×1080 PNG image of the 天地盤, featuring a 12-palace grid and a central information panel.
Results are deterministic — the same input always produces the same divination output.
Provides 大六壬 (Da Liu Ren) divination capabilities for Hermes Agent, allowing AI agents to perform traditional Chinese astrological calculations including 三傳, 四課, 天地盤, 格局, and 神煞, and generate a celestial-earth plate PNG image.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@liuren do a liuren reading for 2024-12-25 18:00"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
점단 일시를 받아 대육임(大六壬) 과를 세워 三傳·四課·天地盤·格局·神煞 텍스트와 천지반 PNG를 반환하는 MCP 서버. (Python 런타임)
구조·네이밍·PNG·설치 규약은
STANDARD.md를 따른다(§6 Python 블록).
점단 엔진: kinliuren — 大六壬 과 생성.
달력 레이어: lunar_python — 일시 → (節氣, 農曆月, 日干支, 時干支) 변환.
⚠️ kinliuren은 간지·절기를 스스로 계산하지 않으므로 이 레이어가 필수다.
절기명은 kinliuren이 기대하는 번체로 보정한다(惊蛰→驚蟄 등).
月將은 점단 시각의 직전 절기(getPrevJieQi)로 결정한다.
렌더: Pillow — 천지반 4×4 그리드, 한글/한자 폰트.
결정론적: 같은 입력 → 같은 과.
간지 변환 신뢰성: 日干支 산출을 천문 JDN 공식(상수 JDN(2000-01-01)=2451545)과 교차검증했다. 예: 2024-02-10 = 甲辰일, 1949-10-01 = 甲子일(만세력 일치).
Related MCP server: mcp-ziwei
get_liuren파라미터 | 타입 | 필수 | 설명 |
| string | ✅* | 점단 일시 |
| object | (선택) 간지 직접 입력 시 달력 변환 생략 |
* manualGanzhi를 주면 datetime_str은 생략 가능.
manualGanzhi 형식: {"jieqi": "立春", "cmonth": 1, "dayGanzhi": "甲辰", "hourGanzhi": "辛未"}
출력 (둘 다 반환):
구조화 텍스트 — 三傳(支·天將·六親·遁干) / 四課 / 天地盤 / 格局 / 神煞(日馬)
천지반 PNG (1080×1080, 12궁 그리드 + 중앙 정보 패널)
예제 출력: examples/liuren_example.png (2024-02-10 14:30).
git clone https://github.com/molpass/mcp-liuren.git
cd mcp-liuren
python -m venv .venv && . .venv/bin/activate # Windows: .venv\Scripts\activate
pip install -r requirements.txt예제 천지반을 직접 생성해 보려면:
python examples/generate-example.py # examples/liuren_example.png 재생성폰트: 한자·한글 라벨을 위해 한글 가능 폰트가 필요하다. Windows는 Malgun Gothic 기본 탑재. Linux는 Noto CJK / Nanum 권장.
liuren, STANDARD §6 Python){
"mcpServers": {
"liuren": {
"command": "/abs/path/mcp-liuren/.venv/bin/python",
"args": ["/abs/path/mcp-liuren/server.py"]
}
}
}
/abs/path는 실제 절대경로로 바꾼다. Windows 예:"command": "C:/Users/<you>/mcp-liuren/.venv/Scripts/python.exe","args": ["C:/Users/<you>/mcp-liuren/server.py"]
페어링 스킬: skill/liuren.skill.md.
Hermes Agent용 MCP — molpass의 바이브 코딩(vibe coding) 프로젝트.
아이디어·방향: molpass (이정훈) · https://zeolinex.com
기획: Claude (Chat)
개발: Claude Code
자가 호스팅 Hermes Agent에 도구로 붙여 쓰는 MCP 서버입니다.
같은 모음:
mcp-saju — 사주명리 만세력
mcp-qr — QR 코드 생성
mcp-biorhythm — 바이오리듬
mcp-astrology — 서양 점성술 네이탈 차트
mcp-ziwei — 자미두수 명반
mcp-numerology — 수비학
mcp-liuren — 대육임
mcp-qimen — 기문둔갑
mcp-taiyi — 태을신수
mcp-weather — 한국 날씨·미세먼지
mcp-newsfeed — 한국 주요뉴스
MIT
대육임 점단을 수행한다.
Args: datetime_str: 점단 일시 "YYYY-MM-DD HH:MM". 수동 간지를 주면 생략 가능. manualGanzhi: (선택) 간지 직접 입력 시 달력 변환을 생략한다. 형식: {"jieqi": "立春", "cmonth": 1, "dayGanzhi": "甲辰", "hourGanzhi": "辛未"}
Returns: 구조화 텍스트(三傳·四課·天地盤·格局·神煞)와 천지반 PNG.
| Name | Required | Description | Default |
|---|---|---|---|
| datetime_str | No | ||
| manualGanzhi | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must cover behavioral traits. It indicates the tool performs a computation (divination) and returns structured text and a PNG, but does not state whether it is read-only, has side effects, or requires specific permissions. The description is not misleading but insufficiently transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise and well-structured: one sentence for purpose, then clearly labeled Args and Returns sections. Every sentence adds value without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's moderate complexity and lack of output schema, the description adequately covers the inputs (with format/optionality) and outputs (structured text + PNG). It could mention edge cases (e.g., what happens if both datetime_str and manualGanzhi are provided or omitted), but overall it is complete enough for an agent to invoke the tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 0% schema description coverage, the description adds meaningful semantics: it explains the format of datetime_str and the optional manualGanzhi's structure with an example (jieqi, cmonth, etc.). This goes beyond the bare schema and helps an agent understand how to use the parameters correctly.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool performs '대육임 점단' (Dae-Yuk-im divination), a specific action on a specific resource. It includes details about arguments and returns, making the purpose unambiguous even without sibling context.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description indirectly provides usage guidance by explaining when to use manualGanzhi ('if you provide manual Ganzi, you can skip calendar conversion'). However, it lacks explicit when-to-use or when-not-to-use statements, and there are no alternatives mentioned due to absence of siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0get_liurenScored across 1 tool
With only one tool, there is no risk of ambiguity. The tool has a clear, distinct purpose.
A single tool named 'get_liuren' follows a conventional verb_noun pattern, and there are no other tools to cause inconsistency.
One tool is too few for typical server scopes. While the server targets a specific divination, additional tools for related operations (e.g., interpretation or history) would improve coverage.
The tool covers the core divination operation, but lacks auxiliary functions like retrieving previous results or validating input, which may limit agent workflows.
BaZi four pillars, Chinese zodiac, lunisolar calendar and almanac days for AI agents.
Generate BaZi charts from birth details. Explore Four Pillars, solar terms, and Luck Pillars for d…
Qimen Dunjia & Da Liu Ren divination: complete nine-palace charts and four-lesson analysis.
BaZi (Chinese Four Pillars) chart calculator. Structured chart data only, no predictions.
