How do I use Saroday MCP Server?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Saroday MCP Server Calculate my Korean Saju for March 15, 1992 at 10am" 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.

de en es ja ko ru zh

Saroday MCP Server

by yolstudio26-oss

Overview Schema Related Servers Score Discussions

JavaScript

Remote

@saroday/mcp-server

MCP (Model Context Protocol) server for Saroday — Korean Saju (사주) calculation and myeongni-hak (命理學) glossary lookup.

This MCP server lets Claude Desktop, Cline, Cursor, and any other MCP-compatible AI client perform accurate Korean Saju (Four Pillars of Destiny) calculation by calling the public Saroday API under the hood.

What it does

When connected, the AI client gains access to four tools:

Tool	Description
`calculate_saju`	Compute full Saju analysis (8 characters, sipseong, sinsal, hapchung, 12-unseong, yongshin, daeun) from birth date / time / gender.
`lookup_glossary`	Look up any of 80+ myeongni-hak terms (도화살, 천을귀인, 식신, 육합, etc.) with full Korean explanation.
`get_daily_fortune`	Today's fortune for one of 12 Western zodiac signs or 12 Chinese zodiac signs. Cached server-side, fast response.
`discover_saroday_api`	List available Saroday API endpoints and metadata.

Why this matters: ChatGPT, Claude, and other LLMs frequently miscalculate Saju when asked directly because manse-ryeok (萬歲曆) lookup and 절기 (jeolgi) boundary handling require precise data. This MCP delegates the math to a verified server while letting the AI focus on the interpretation.

Related MCP server: 命盘 Mingpan

Installation

Option A — npx (no install)

npx @saroday/mcp-server

Option B — global install

npm install -g @saroday/mcp-server
saroday-mcp

Option C — clone and run

git clone https://github.com/saroday/mcp-server.git
cd mcp-server
npm install
node index.js

Requires Node.js 18 or newer.

Configure Claude Desktop

Edit your Claude Desktop config file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json

Add (or merge) the following:

{
  "mcpServers": {
    "saroday": {
      "command": "npx",
      "args": ["-y", "@saroday/mcp-server"]
    }
  }
}

Restart Claude Desktop. You should see "saroday" listed in the MCP servers panel (the plug icon in the input area).

Local development (running from cloned repo)

{
  "mcpServers": {
    "saroday": {
      "command": "node",
      "args": ["/absolute/path/to/mcp-server/index.js"]
    }
  }
}

Configure Cline / Cursor / other MCP clients

Any MCP client that supports stdio transport works. Point it at the saroday-mcp binary or node index.js. See your client's docs for the exact config format.

Try it out

After connecting, ask Claude things like:

"My birthday is March 15, 1992 at 10am. Calculate my Korean Saju."
"What does 도화살 (dohwa-sal) mean in Korean fortune-telling?"
"내 사주 봐줘. 1990년 5월 20일 음력 14시 여성."
"제왕(jeokwang) 12-unseong이 뭐야?"

Claude will automatically invoke calculate_saju or lookup_glossary and give you a polished interpretation based on the structured data returned.

Environment variables

Variable	Default	Purpose
`SARODAY_API_BASE`	`https://saroday.com`	Override the API base URL (e.g., for self-hosted or staging environments).

Rate limits

The public Saroday API allows 100 requests per hour per IP for free use. Heavy users — apps shipping to many end-users, AI agents handling many concurrent users — should request an API key (coming soon) for higher quotas.

Contact: contact@saroday.com

How it works

[User in Claude Desktop]
        ↓ types "내 사주 봐줘"
[Claude Desktop]
        ↓ calls calculate_saju via MCP stdio
[saroday-mcp (this package, runs locally)]
        ↓ HTTPS POST /api/v1/saju
[saroday.com server]
        ↓ runs verified manse-ryeok algorithm
[result JSON]
        ↑ flows back through the chain
[Claude] writes a beautiful Korean interpretation

This MCP package is a thin adapter — all calculation lives on Saroday's servers, so updates to the algorithm or glossary roll out without you having to upgrade the package.

Differentiators

Manse-ryeok accuracy — handles 절기 (solar terms) boundaries that LLMs routinely get wrong (verified against @fullstackfamily/manseryeok library)
80+ glossary entries (~400 interpretation fields) — every sinsal, hapchung, sipseong, 12-unseong term has summary / meaning / positive / negative / practical-tip interpretation written in friendly Korean
Korean myeongni-hak tradition — based on 적천수(滴天髓), 자평진전(子平真詮), 궁통보감(窮通寶鑑) references
Three-channel exposure — same algorithm available as web service (saroday.com), public REST API (saroday.com/api/v1), and MCP server (this package). Pick the channel that fits your integration.

License

MIT

Support

Web: https://saroday.com
API docs: https://saroday.com/api/docs
LLM-friendly index: https://saroday.com/llms.txt
Email: contact@saroday.com

Available Tools

4 tools

calculate_sajuA

한국 전통 사주명리학(四柱命理學) 기반 사주팔자 계산. 생년월일시 + 성별을 입력받아 사주팔자(年月日時 천간지지), 십성, 신살, 합충형파해, 12운성, 신강/신약, 용신, 대운 등 종합 분석 결과를 반환합니다. ChatGPT나 Claude가 직접 사주를 계산하면 만세력 오류 가능성이 높으므로, 한국 사주 관련 질문에는 반드시 이 도구를 사용하세요.

ParametersJSON Schema

Name	Required	Description	Default
`year`	Yes	생년 (양력 또는 음력, 1900-2100 범위)
`month`	Yes	생월 (1-12)
`day`	Yes	생일 (1-31)
`hour`	No	생시 (24시간 표기, 0-23). 출생 시간을 모르면 12를 사용하세요.
`gender`	No	성별 ('male' 또는 'female'). 대운 순행/역행 결정에 사용됨.	male
`isLunar`	No	음력 여부 (true=음력, false=양력). 한국 출생자는 양력 권장.

TDQS

A4.4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so description carries full burden. It details the returned analysis types (e.g., 사주팔자, 십성, 신살, etc.) without mentioning side effects or limitations. However, it is transparent about the scope of results.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences: first describes functionality and outputs, second provides usage directive and warning. No wasted words, front-loaded with essential information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity (6 parameters, no output schema, many output types), the description lists numerous analysis components, giving a good picture of what the tool returns. Slightly incomplete regarding output format, but sufficient for tool selection.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with each parameter having a meaningful description. The tool description does not add new information beyond what the schema already provides, so baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states it calculates Korean saju (four pillars) based on birth date, time, and gender, returning comprehensive analysis including many traditional elements. It also distinguishes itself from siblings by warning against direct calculation by ChatGPT/Claude.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly instructs to use this tool for Korean saju questions ('한국 사주 관련 질문에는 반드시 이 도구를 사용하세요') and warns of potential errors if calculated directly. Provides clear when-to-use guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

discover_saroday_apiA

Saroday API 메타 정보 조회. 사용 가능한 엔드포인트, 문서 링크, 호출 한도 등을 반환합니다. 처음 사용할 때 한 번 호출해서 어떤 도구가 있는지 파악할 수 있습니다.

ParametersJSON Schema

Name	Required	Description	Default
No parameters

TDQS

A4.3/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It states the tool returns metadata and implies it is read-only and safe. However, it does not explicitly confirm no destructive effects, auth requirements, or rate limits for this tool itself. This is adequate but could be more explicit.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences: the first clearly defines the tool's purpose, and the second provides usage guidance. It is front-loaded, concise, and contains no extraneous information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a parameterless tool with no output schema and a simple metadata purpose, the description fully covers what the tool does, what it returns, and when to use it. Sibling tools are distinct, so the agent can correctly infer its role.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has no parameters, and schema description coverage is 100%. The description implicitly indicates that no parameters are needed ('call once'). It does not need to add param details, though it could explicitly state 'no parameters required.'

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states that the tool retrieves metadata (endpoints, docs, rate limits) about the Saroday API. It distinguishes itself from sibling tools like calculate_saju, get_daily_fortune, and lookup_glossary, which are specific application tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly advises calling this tool once at first use to understand available tools. This provides clear when-to-use guidance, though it does not mention when not to use it or specify alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_daily_fortuneA

오늘의 운세 조회 (별자리 또는 띠). 한국 사용자가 가장 자주 보는 운세 카테고리. 사용자가 '오늘의 운세 봐줘', '내 별자리 오늘 어때?', '말띠 오늘 운세' 같은 질문을 할 때 사용하세요. GPT 기반 자연어 운세지만 사로 서버에서 하루 한 번만 생성하고 캐시하므로 응답 빠름.

ParametersJSON Schema

Name	Required	Description	Default
`type`	Yes	'zodiac' = 서양 별자리 (12개), 'chinese' = 동양 띠 (12개)
`sign`	Yes	별자리 또는 띠 ID. zodiac: aries, taurus, gemini, cancer, leo, virgo, libra, scorpio, sagittarius, capricorn, aquarius, pisces. chinese: rat, ox, tiger, rabbit, dragon, snake, horse, sheep, monkey, rooster, dog, pig. 사용자 생년월일을 받았다면 자체적으로 계산하여 ID 추론 후 호출.

TDQS

A4.4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, but description adds valuable behavioral context: GPT-based but cached daily for fast response. Does not contradict any annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Four sentences front-loaded with purpose, then usage examples and technical detail. No redundancy; every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema, but description provides enough for an agent to understand purpose and when to call. Missing return format is a minor gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, baseline 3. Description adds example queries, explains enum values, and mentions automatic sign inference from birth date, surpassing schema alone.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states '오늘의 운세 조회 (별자리 또는 띠)' and provides example user queries, making the purpose specific and distinguishing from siblings like calculate_saju.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Describes when to use with example queries and notes the cached nature. Lacks explicit exclusions or alternatives but context from siblings suffices.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

lookup_glossaryA

명리학 용어 풀이 조회. 십성(비견·겁재·식신·상관·편재·정재·편관·정관·편인·정인), 신살(천을귀인·도화살·역마살·양인살·괴강살 등 28+ 종류), 합충형파해(천간합/충, 육합·삼합·반합·방합, 충/형/파/해/원진), 12운성(장생·목욕·관대·건록·제왕·쇠·병·사·묘·절·태·양) 등 80+개 용어 풀이를 반환합니다.

ParametersJSON Schema

Name	Required	Description	Default
`term`	Yes	조회할 명리학 용어 (한글). 예: '도화살', '식신', '천을귀인', '육합', '제왕'

TDQS

A3.9/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided. The description indicates a read-only lookup returning definitions, but does not disclose whether it is idempotent, any authentication requirements, or rate limits. With no annotations, the description carries the full burden but only states what it does, not behavioral traits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Single-sentence description is front-loaded with the core action, then lists categories. It is informative but somewhat long; could be split for readability. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simple input (1 param, no output schema), the description adequately covers the tool's purpose and scope. It does not mention if the term is case-sensitive or if partial matches are allowed, but the example terms compensate. Reasonably complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% (parameter 'term' described in both schema and description). The description adds value by listing example terms and categories, providing context beyond the schema's generic description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it looks up glossary terms for Myeongrihak, listing specific categories (십성, 신살, 합충형파해, 12운성) and over 80 terms. The verb '조회' and resource '명리학 용어 풀이' are specific, distinguishing it from sibling tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use versus alternatives. The context signals show sibling tools like calculate_saju, but the description does not compare them or provide exclusions. Usage is implied: lookup a term when you need its definition.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

4 tool updatesv0.1.0Apr 26, 2026
- First observedcalculate_saju
- First observeddiscover_saroday_api
- First observedget_daily_fortune
- First observedlookup_glossary

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4.4/5.0

Disambiguation5/5

Each tool has a clearly distinct purpose: calculate_saju computes fortune using traditional methods, discover_saroday_api provides API metadata, get_daily_fortune offers daily horoscopes, and lookup_glossary explains terminology. No overlap in functionality.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern using snake_case: calculate_saju, discover_saroday_api, get_daily_fortune, lookup_glossary. No deviation in style.

Tool Count5/5

With 4 tools, the server is well-scoped for its domain of Korean fortune telling. Each tool serves an essential function without redundancy or unnecessary complexity.

Completeness5/5

The tool set covers the core aspects of the domain: personal fortune calculation (saju), daily fortune, glossary reference, and API discovery. No obvious gaps for the stated purpose.

Maintenance

ActivityInactive

ResponsivenessNo issues

Resources

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Q Fortune
uk.ugot.fortune
Korean saju fortune MCP: natal chart, today/daily/yearly luck, compatibility, and saved profiles.
Entertainment & Media
1
bazi-api A
io.github.ghdejr11-beep
Deterministic Korean Saju / BaZi Four Pillars MCP. Day Master, five elements, compatibility.
Art & Culture
22
VedaVisor Vedic Astrology MCP A
io.github.dchhill
Professional Vedic astrology tools for AI agents via MCP.
Entertainment & Media
3
korean-saju-calculator A
io.github.minjikim89
Korean Four Pillars (Saju/BaZi) calculator: pillars, elements, ten gods, sinsal, luck cycles.
Art & Culture
12

Related MCP Servers

taibu
AI & Machine Learning
hhszzzz
F
license
Not graded
quality
B
maintenance
Enables traditional Chinese metaphysics tools like Bazi, Ziwei, and Qimen via MCP, integrating AI analysis for divination and fortune-telling.
Updated a month ago (2026-08-01 10:15 UTC)
516
-
命盘 Mingpan
Art & Culture
ChesterRa
A
license
A
quality
A
maintenance
Provides traditional Chinese astrology (Bazi, Ziwei) and divination (Liuyao, Meihua, Qimen, etc.) calculations as MCP tools for AI assistants.
Updated 3 days ago (2026-09-03 09:05 UTC)
17
230
106
Apache 2.0
Saju MCP Server
Art & Culture
ghdejr11-beep
F
license
A
quality
B
maintenance
Enables MCP clients to compute and interpret Korean Four Pillars of Destiny (Saju) through natural language, including calculation, interpretation, compatibility analysis, and daily fortune.
Updated 2 months ago (2026-06-28 09:34 UTC)
4
43
-
Saju Concierge
Entertainment & Media
bb4rjfl
F
license
Not graded
quality
B
maintenance
MCP server that calculates saju (four pillars) from birth date/time and provides entertaining interpretations of daily fortune, yearly luck, compatibility, name analysis, and tarot using MIT-licensed manseryeok-js.
Updated 2 months ago (2026-07-03 03:56 UTC)
-

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/yolstudio26-oss/saroday-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server