Saju MCP Server
Enables MCP clients to compute and interpret Korean Four Pillars of Destiny (Saju) through natural language, including calculation, interpretation, compatibility analysis, and daily fortune.
README
Saju MCP Server
An MCP (Model Context Protocol) server that wraps the Saju API — Korean Four Pillars of Destiny (사주팔자 / Bazi) — so MCP-capable clients (Claude Desktop, Cursor, and other MCP hosts) can compute and interpret Saju directly in a conversation.
Backed by the live API at https://saju-api.pages.dev (10 languages: ko, en, ja, zh, es, pt-br, vi, id, hi, th).
Tools
| Tool | Upstream endpoint | What it does |
|---|---|---|
saju_calculate |
POST /api/v1/calculate |
Four Pillars (stem+branch+hanja), five-element distribution, Day Master, zodiac, from a solar birthdate. |
saju_interpret |
POST /api/v1/interpret |
Full reading: Ten Gods (십신), hidden stems, Yongshin (용신), Daeun (대운), localized summaries. |
saju_compatibility |
POST /api/v1/compatibility |
Two-person 궁합 score (0–100) with breakdown (element balance, Day Master relation, branch harmony/clash). |
saju_daily |
GET /api/v1/daily |
Daily fortune snapshot (score + advice) for a Day Master and date. |
Prerequisites
- Node.js 18+ (uses the built-in global
fetch). - A Saju API key. The free tier is 100 requests/day, no credit card.
Get a free API key
curl -X POST https://saju-api.pages.dev/api/v1/keys/create \
-H "Content-Type: application/json" \
-d '{"email":"you@example.com"}'
The response contains an api_key of the form sajuapi_free_.... Keep it
secret — it is passed to the server via the SAJU_API_KEY environment variable,
never hardcoded.
Install & build
npm install
npm run build # compiles src/index.ts -> dist/index.js
Quick local check (lists the 4 tools, then exits):
SAJU_API_KEY="sajuapi_free_xxx" npm start
Register in Claude Desktop
Edit your claude_desktop_config.json:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
Add (use the absolute path to the built dist/index.js):
{
"mcpServers": {
"saju": {
"command": "node",
"args": ["D:\\kunstudio-apps\\saju-mcp\\dist\\index.js"],
"env": {
"SAJU_API_KEY": "sajuapi_free_your_key_here"
}
}
}
}
Restart Claude Desktop. The four saju_* tools appear in the tools menu.
Other MCP hosts (Cursor, Windsurf, custom clients) use the same shape:
command: "node",args: ["<abs path>/dist/index.js"], and aSAJU_API_KEYenv var.
Environment variables
| Variable | Required | Default | Notes |
|---|---|---|---|
SAJU_API_KEY |
yes (for real calls) | (empty) | Your sajuapi_* key, sent as the X-API-Key header. Without it, every call returns 401 invalid_api_key. |
SAJU_API_BASE |
no | https://saju-api.pages.dev |
Override the upstream base URL (e.g. for a staging deploy). |
Example tool inputs
saju_calculate / saju_interpret:
{ "year": 1990, "month": 5, "day": 15, "hour": 14, "gender": "M", "lang": "en" }
(hour: -1 if the birth hour is unknown.)
saju_compatibility:
{
"person_a": { "year": 1990, "month": 5, "day": 15, "hour": 14, "gender": "M" },
"person_b": { "year": 1992, "month": 8, "day": 3, "hour": 9, "gender": "F" },
"lang": "en"
}
saju_daily (Day Master from a prior calculate/interpret call):
{ "day_master": "갑", "date": "2026-06-17", "lang": "en" }
License
Proprietary — KunStudio. Wraps the Saju API; subject to that API's terms.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。