# Legend Saju (remote · legend-saju-mcp-production.up.railway.app)

Source-traceable Saju, Zi Wei, Qimen, Daliuren, Tieban, naming, and related calculations

- Trust score: 84/100 (high trust)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-21

## Components

- remote · `legend-saju-mcp-production.up.railway.app`: 84/100 (this document), [markdown](https://verifymcp.io/servers/sihyeonjeon-legend-saju/legend-saju-mcp-production.md), [page](https://verifymcp.io/servers/sihyeonjeon-legend-saju/legend-saju-mcp-production)

## Channel facts

- Endpoint: `https://legend-saju-mcp-production.up.railway.app/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.4.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-21.

- **Endpoint Security**: 74/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 75/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 3604 tokens (~212/item across 17 items; 13 tools + 4 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 97/100
  - Stability observed for 29 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 87/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 56% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 13 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 15 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).
  - Supports UI / widget rendering.

## Install

### How do I install the Legend Saju MCP server?

Legend Saju is a hosted endpoint at https://legend-saju-mcp-production.up.railway.app/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http sihyeonjeon-legend-saju 'https://legend-saju-mcp-production.up.railway.app/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "sihyeonjeon-legend-saju": {
      "url": "https://legend-saju-mcp-production.up.railway.app/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "sihyeonjeon-legend-saju": {
      "type": "http",
      "url": "https://legend-saju-mcp-production.up.railway.app/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.sihyeonjeon-legend-saju]
url = "https://legend-saju-mcp-production.up.railway.app/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "sihyeonjeon-legend-saju": {
      "type": "remote",
      "url": "https://legend-saju-mcp-production.up.railway.app/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add sihyeonjeon-legend-saju --url 'https://legend-saju-mcp-production.up.railway.app/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  sihyeonjeon-legend-saju:
    url: "https://legend-saju-mcp-production.up.railway.app/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "sihyeonjeon-legend-saju": {
      "Transport": "http",
      "Url": "https://legend-saju-mcp-production.up.railway.app/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add sihyeonjeon-legend-saju -t streamable-http -u 'https://legend-saju-mcp-production.up.railway.app/mcp'
```

### Other

```json
{
  "mcpServers": {
    "sihyeonjeon-legend-saju": {
      "type": "http",
      "url": "https://legend-saju-mcp-production.up.railway.app/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-21 (score 84, +1)

No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-19 (score 83, +1)

No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-17 (score 82, +1)

No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-15 (score 81, +1)

No change was recorded against any check on this day. Stability & Change Management went from 73 to 77. That category is still filling its 30-day observation window: 22 days of observed history at the previous scan, 23 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-13 (score 80, +1)

No change was recorded against any check on this day. Stability & Change Management went from 67 to 70. That category is still filling its 30-day observation window: 20 days of observed history at the previous scan, 21 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-11 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 60 to 63. That category is still filling its 30-day observation window: 18 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-09 (score 78, +1)

No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-06 (score 77, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (13)

### `legend_saju_manifest` (~28 tokens)

Inspect Legend Saju

Return the live, source-traceable deterministic engine manifest. No model or network call.

Output parameters:

- `capabilities` (object)
- `capabilityCount` (integer)
- `deterministic` (boolean)
- `error` (string)
- `knowledge`
- `legacyIntentCount` (integer)
- `naming`
- `publicationSideEffects` (boolean)
- `sourceCount` (integer)
- `version` (string)

### `legend_saju_capabilities` (~99 tokens)

Find a calculation method

Use this when a user asks which Saju, Myeongri, Zi Wei, Qimen, Daliuren, I Ching, Tieban, Dang Saju, Tojeong, Feng Shui, naming, dream, or other traditional calculation method fits a specialized question. Do not use it for an ordinary fortune reading.

Input parameters:

- `limit` (integer)
- `query` (string)
- `systems` (array)

Output parameters:

- `capabilityCount` (integer)
- `error` (string)
- `hits` (array)
- `query` (string)
- `requestedCapabilityContract` (string)

### `legend_saju_read_fortune` (~347 tokens)

Read a Saju fortune

Use this for natal, current, annual, career, wealth, relationship, health, and action readings. Use detailLevel for calculation breadth and outputMode for action, readable, evidence, or debug results. Consumer responses always carry verdicts (왕쇠·격국·용신 후보 conclusions) plus an evidenceIndex of omitted internal claims; repeat the identical call with claimIds from that index to selectively pull deeper grounding such as strength axes, pattern structure, or methodology notes.

Input parameters:

- `asOfYear` (integer)
- `birth` (object, required)
- `claimIds` (array): Fetch port: repeat the previous call with identical inputs and pass claim IDs from evidenceIndex or evidenceClaimIds to receive those claims in full (statement, observations, sources, limitations) in…
- `detailLevel` (string): Calculation breadth. This does not choose the response projection.
- `lifeEvents` (array)
- `maxClaims` (integer): Global item budget outside debug mode. It limits interpretations, actions, timeline entries, claims, legacy evidence, and method results together.
- `outputMode` (string): Response projection: action_only returns actions, consumer returns a readable interpretation, evidence returns claims and source-linked method data, and debug returns the internal resolver record.
- `question` (string, required): The user's original request, such as 올해 재물운과 사업운을 봐줘.
- `targetDate` (object): The date whose current or future fortune is being read. Supply the current local date for requests such as 올해 운세 or 현재 운세.
- `timelineRange` (object)

Output parameters:

- `blocked` (array)
- `calculationSummary` (object)
- `claimDetails` (array)
- `claims` (array)
- `conflicts` (array)
- `detailLevel` (string)
- `dossier`
- `dreamAnalysis` (object)
- `dreamSummary` (object)
- `error` (string)
- `evidence` (array)
- `evidenceIndex` (object)
- `executionPlan` (object)
- `inputNotes` (array)
- `methodAnalysis` (object)
- `mode` (string)
- `nameAnalysis`
- `nameSummary` (object)
- `noModelCalls` (boolean)
- `omittedItemsByKind` (object)
- `omittedTimelineYears` (integer)
- `publicationSideEffects` (boolean)
- `question` (string)
- `readingSummary` (object)
- `recommendations`
- `routes` (array)
- `sections` (object)
- `selection`
- `sources` (array)
- `timeline` (array)
- `unmatchedClaimIds` (array)
- `verdicts` (object)

### `legend_saju_analyze_compatibility` (~237 tokens)

Analyze two-person compatibility

Use this when the user asks 궁합, 결혼 가능성, relationship compatibility, or wants two birth charts compared. Requires both people's birth data.

Input parameters:

- `birth` (object, required)
- `claimIds` (array): Fetch port: repeat the previous call with identical inputs and pass claim IDs from evidenceIndex or evidenceClaimIds to receive those claims in full (statement, observations, sources, limitations) in…
- `detailLevel` (string): Calculation breadth. This does not choose the response projection.
- `lifeEvents` (array)
- `maxClaims` (integer): Global item budget outside debug mode. It limits interpretations, actions, timeline entries, claims, legacy evidence, and method results together.
- `outputMode` (string): Response projection: action_only returns actions, consumer returns a readable interpretation, evidence returns claims and source-linked method data, and debug returns the internal resolver record.
- `partnerBirth` (object, required)
- `question` (string, required): What the user wants to know about the relationship.
- `targetDate` (object)

Output parameters:

- `blocked` (array)
- `calculationSummary` (object)
- `claimDetails` (array)
- `claims` (array)
- `conflicts` (array)
- `detailLevel` (string)
- `dossier`
- `dreamAnalysis` (object)
- `dreamSummary` (object)
- `error` (string)
- `evidence` (array)
- `evidenceIndex` (object)
- `executionPlan` (object)
- `inputNotes` (array)
- `methodAnalysis` (object)
- `mode` (string)
- `nameAnalysis`
- `nameSummary` (object)
- `noModelCalls` (boolean)
- `omittedItemsByKind` (object)
- `omittedTimelineYears` (integer)
- `publicationSideEffects` (boolean)
- `question` (string)
- `readingSummary` (object)
- `recommendations`
- `routes` (array)
- `sections` (object)
- `selection`
- `sources` (array)
- `timeline` (array)
- `unmatchedClaimIds` (array)
- `verdicts` (object)

### `legend_saju_select_dates` (~258 tokens)

Select auspicious dates

Use this only when the user explicitly asks for 택일, 좋은 날, 계약일, 이사일, 개업일, 수술일, or another date-selection task. Do not use it merely because a fortune request mentions this year.

Input parameters:

- `birth` (object, required)
- `claimIds` (array): Fetch port: repeat the previous call with identical inputs and pass claim IDs from evidenceIndex or evidenceClaimIds to receive those claims in full (statement, observations, sources, limitations) in…
- `detailLevel` (string): Calculation breadth. This does not choose the response projection.
- `maxClaims` (integer): Global item budget outside debug mode. It limits interpretations, actions, timeline entries, claims, legacy evidence, and method results together.
- `outputMode` (string): Response projection: action_only returns actions, consumer returns a readable interpretation, evidence returns claims and source-linked method data, and debug returns the internal resolver record.
- `purpose` (string)
- `question` (string, required): The event and constraints for choosing a date.
- `rangeDays` (integer)
- `targetDate` (object, required): Start date for the candidate range.

Output parameters:

- `blocked` (array)
- `calculationSummary` (object)
- `claimDetails` (array)
- `claims` (array)
- `conflicts` (array)
- `detailLevel` (string)
- `dossier`
- `dreamAnalysis` (object)
- `dreamSummary` (object)
- `error` (string)
- `evidence` (array)
- `evidenceIndex` (object)
- `executionPlan` (object)
- `inputNotes` (array)
- `methodAnalysis` (object)
- `mode` (string)
- `nameAnalysis`
- `nameSummary` (object)
- `noModelCalls` (boolean)
- `omittedItemsByKind` (object)
- `omittedTimelineYears` (integer)
- `publicationSideEffects` (boolean)
- `question` (string)
- `readingSummary` (object)
- `recommendations`
- `routes` (array)
- `sections` (object)
- `selection`
- `sources` (array)
- `timeline` (array)
- `unmatchedClaimIds` (array)
- `verdicts` (object)

### `legend_saju_cast_divination` (~276 tokens)

Cast a traditional divination chart

Use this for 기문둔갑, 대육임, 주역, 점괘, or a concrete decision cast from a question time or six line values. Do not use it for a general natal fortune reading.

Input parameters:

- `birth` (object): Optional natal input when the requested method needs it.
- `claimIds` (array): Fetch port: repeat the previous call with identical inputs and pass claim IDs from evidenceIndex or evidenceClaimIds to receive those claims in full (statement, observations, sources, limitations) in…
- `detailLevel` (string): Calculation breadth. This does not choose the response projection.
- `lineValues` (array): Six I Ching line values, bottom line first.
- `maxClaims` (integer): Global item budget outside debug mode. It limits interpretations, actions, timeline entries, claims, legacy evidence, and method results together.
- `outputMode` (string): Response projection: action_only returns actions, consumer returns a readable interpretation, evidence returns claims and source-linked method data, and debug returns the internal resolver record.
- `question` (string, required): The concrete decision or divination question.
- `questionDateTime` (object): Casting moment for Qimen, Daliuren, or Tieban question-time calculations.

Output parameters:

- `blocked` (array)
- `calculationSummary` (object)
- `claimDetails` (array)
- `claims` (array)
- `conflicts` (array)
- `detailLevel` (string)
- `dossier`
- `dreamAnalysis` (object)
- `dreamSummary` (object)
- `error` (string)
- `evidence` (array)
- `evidenceIndex` (object)
- `executionPlan` (object)
- `inputNotes` (array)
- `methodAnalysis` (object)
- `mode` (string)
- `nameAnalysis`
- `nameSummary` (object)
- `noModelCalls` (boolean)
- `omittedItemsByKind` (object)
- `omittedTimelineYears` (integer)
- `publicationSideEffects` (boolean)
- `question` (string)
- `readingSummary` (object)
- `recommendations`
- `routes` (array)
- `sections` (object)
- `selection`
- `sources` (array)
- `timeline` (array)
- `unmatchedClaimIds` (array)
- `verdicts` (object)

### `legend_saju_analyze_name` (~259 tokens)

Analyze a Korean name

Use this for 작명, 성명학, 81수, 이름 한자, 인명용 한자, 획수, or 파자 questions. It keeps legal Hanja observations, declared stroke standards, and birth-based naming guidance separate.

Input parameters:

- `birth` (object)
- `claimIds` (array): Fetch port: repeat the previous call with identical inputs and pass claim IDs from evidenceIndex or evidenceClaimIds to receive those claims in full (statement, observations, sources, limitations) in…
- `detailLevel` (string): Calculation breadth. This does not choose the response projection.
- `givenStrokes` (array)
- `maxClaims` (integer): Global item budget outside debug mode. It limits interpretations, actions, timeline entries, claims, legacy evidence, and method results together.
- `name` (object)
- `outputMode` (string): Response projection: action_only returns actions, consumer returns a readable interpretation, evidence returns claims and source-linked method data, and debug returns the internal resolver record.
- `question` (string, required): Name, Hanja, stroke-count, or naming question.
- `surnameStrokes` (array)

Output parameters:

- `blocked` (array)
- `calculationSummary` (object)
- `claimDetails` (array)
- `claims` (array)
- `conflicts` (array)
- `detailLevel` (string)
- `dossier`
- `dreamAnalysis` (object)
- `dreamSummary` (object)
- `error` (string)
- `evidence` (array)
- `evidenceIndex` (object)
- `executionPlan` (object)
- `inputNotes` (array)
- `methodAnalysis` (object)
- `mode` (string)
- `nameAnalysis`
- `nameSummary` (object)
- `noModelCalls` (boolean)
- `omittedItemsByKind` (object)
- `omittedTimelineYears` (integer)
- `publicationSideEffects` (boolean)
- `question` (string)
- `readingSummary` (object)
- `recommendations`
- `routes` (array)
- `sections` (object)
- `selection`
- `sources` (array)
- `timeline` (array)
- `unmatchedClaimIds` (array)
- `verdicts` (object)

### `legend_saju_interpret_dream` (~283 tokens)

Interpret a dream from audited traditions

Use this for 해몽, 꿈풀이, or dream interpretation. It currently handles five cross-culturally audited concepts and returns both shared motifs and conflicting conditions with primary-source excerpts; it does not turn the remaining raw corpus into invented meanings.

Input parameters:

- `claimIds` (array): Fetch port: repeat the previous call with identical inputs and pass claim IDs from evidenceIndex or evidenceClaimIds to receive those claims in full (statement, observations, sources, limitations) in…
- `detailLevel` (string): Calculation breadth. This does not choose the response projection.
- `dream` (string, required): The dream narrative. Preserve the user's details instead of reducing it to one symbol.
- `dreamContext` (string): Only context the user actually supplied, such as emotion, setting, relationships, work, or health.
- `maxClaims` (integer): Global item budget outside debug mode. It limits interpretations, actions, timeline entries, claims, legacy evidence, and method results together.
- `maxDreamMatches` (integer)
- `outputMode` (string): Response projection: action_only returns actions, consumer returns a readable interpretation, evidence returns claims and source-linked method data, and debug returns the internal resolver record.
- `question` (string, required): What the user wants to understand about the dream.

Output parameters:

- `blocked` (array)
- `calculationSummary` (object)
- `claimDetails` (array)
- `claims` (array)
- `conflicts` (array)
- `detailLevel` (string)
- `dossier`
- `dreamAnalysis` (object)
- `dreamSummary` (object)
- `error` (string)
- `evidence` (array)
- `evidenceIndex` (object)
- `executionPlan` (object)
- `inputNotes` (array)
- `methodAnalysis` (object)
- `mode` (string)
- `nameAnalysis`
- `nameSummary` (object)
- `noModelCalls` (boolean)
- `omittedItemsByKind` (object)
- `omittedTimelineYears` (integer)
- `publicationSideEffects` (boolean)
- `question` (string)
- `readingSummary` (object)
- `recommendations`
- `routes` (array)
- `sections` (object)
- `selection`
- `sources` (array)
- `timeline` (array)
- `unmatchedClaimIds` (array)
- `verdicts` (object)

### `legend_saju_card_natal` (~134 tokens)

원국 카드 렌더링

Render a natal-chart card (사주 봐주세요·원국 풀이·신살 질문). Shows four pillars, day-master identity, element balance, 왕쇠·격국·용신 verdicts, 신살, and 합충. Compute chart facts server-side and render them in a widget card. Write the narrative/text fields yourself, grounded in a prior legend_saju_read_fortune call — the card labels them as AI interpretation. After the card renders, add only brief text the card does not already show.

Input parameters:

- `birth` (object, required)
- `narrative` (object)

Output parameters:

- `widget` (string)

### `legend_saju_card_fortune` (~197 tokens)

운세 카드 렌더링

Render domain fortune cards (재물운·연애운·결혼운·직업운·건강운·학업운·이동운·재회운·총운). Pick only the domains the user asked about and write each card's text yourself. Compute chart facts server-side and render them in a widget card. Write the narrative/text fields yourself, grounded in a prior legend_saju_read_fortune call — the card labels them as AI interpretation. After the card renders, add only brief text the card does not already show.

Input parameters:

- `actions` (array): 개운 action checklist.
- `asOfYear` (integer)
- `birth` (object, required)
- `cards` (array, required): Pick only the domains the user asked about.
- `narrative` (object)
- `title` (string): Report title, e.g. 2026년 하반기 운세.

Output parameters:

- `widget` (string)

### `legend_saju_card_compatibility` (~177 tokens)

궁합 카드 렌더링

Render a two-person compatibility card (사주 궁합 봐주세요). Shows both day pillars and deterministic 합·충·형·파·해 signals. Compute chart facts server-side and render them in a widget card. Write the narrative/text fields yourself, grounded in a prior legend_saju_read_fortune call — the card labels them as AI interpretation. After the card renders, add only brief text the card does not already show.

Input parameters:

- `birthA` (object, required)
- `birthB` (object, required)
- `nameA` (string): Display label such as 나, 그 사람, or a first name the user supplied.
- `nameB` (string)
- `narrative` (object)
- `score` (integer): Assistant's editorial 1–5 harmony score, rendered as hearts.

Output parameters:

- `widget` (string)

### `legend_saju_card_timeline` (~176 tokens)

대운 타임라인 렌더링

Render the 대운 flow timeline (대운 흐름·결혼 시기·이직/창업 시기 질문). Marks the current 대운 and an optional focus year with its 세운. Compute chart facts server-side and render them in a widget card. Write the narrative/text fields yourself, grounded in a prior legend_saju_read_fortune call — the card labels them as AI interpretation. After the card renders, add only brief text the card does not already show.

Input parameters:

- `asOfYear` (integer)
- `birth` (object, required)
- `focusNote` (string): Assistant's one-line note about the focus year.
- `focusYear` (integer): Year the user is asking about (결혼·이직·창업 시기 등).
- `narrative` (object)

Output parameters:

- `widget` (string)

### `legend_saju_run_methods` (~631 tokens)

Run specific or mixed traditional methods

Use this for expert, mixed-system, or named-method requests. It covers Myeongri details such as 십성·지장간·투간·통근·합충형파해·삼합·방합·육합·월령·격국·조후·억부·통관·병약·궁통보감·적천수·삼명통회·연해자평·종격·화격·특수격; Zi Wei 12궁·삼방사정·대한·유년·유월·유일·유시·생년사화·궁간사화·자화·비성·흠천사화·중주파; and Qimen, Daliuren, I Ching, Tieban, Dang Saju, Tojeong, Feng Shui, naming, 81-number, Hanja decomposition, and dream traditions. Pass discovered capability IDs together in requestedCapabilities, or let the server plan from the question. Use focused tools for ordinary single-goal requests.

Input parameters:

- `asOfYear` (integer)
- `birth` (object)
- `claimIds` (array): Fetch port: repeat the previous call with identical inputs and pass claim IDs from evidenceIndex or evidenceClaimIds to receive those claims in full (statement, observations, sources, limitations) in…
- `detailLevel` (string): Calculation breadth. This does not choose the response projection.
- `dream` (string): Dream narrative for the source-bounded cross-cultural dream engine.
- `dreamContext` (string): Optional emotion, setting, relationship, work, health, or other context explicitly supplied by the user.
- `givenStrokes` (array)
- `lifeEvents` (array)
- `lineValues` (array)
- `maxAutoCapabilities` (integer)
- `maxClaims` (integer): Global item budget outside debug mode. It limits interpretations, actions, timeline entries, claims, legacy evidence, and method results together.
- `maxDreamMatches` (integer)
- `name` (object): Actual Korean name characters for the separate 9,495-entry official-name analysis path.
- `outputMode` (string): Response projection: action_only returns actions, consumer returns a readable interpretation, evidence returns claims and source-linked method data, and debug returns the internal resolver record.
- `partnerBirth` (object)
- `purpose` (string)
- `question` (string, required): Open-ended question. Built-in routing terms cover Korean plus common English, Chinese, and Japanese metaphysics vocabulary.
- `questionDateTime` (object): Moment a Qimen, Daliuren, or question-time calculation is cast.
- `rangeDays` (integer)
- `requestedCapabilities` (array): Optional runtime IDs from legend_saju_capabilities. This is intentionally not an enum.
- `surnameStrokes` (array)
- `targetDate` (object): Date or range anchor being analyzed.
- `timelineRange` (object)

Output parameters:

- `blocked` (array)
- `calculationSummary` (object)
- `claimDetails` (array)
- `claims` (array)
- `conflicts` (array)
- `detailLevel` (string)
- `dossier`
- `dreamAnalysis` (object)
- `dreamSummary` (object)
- `error` (string)
- `evidence` (array)
- `evidenceIndex` (object)
- `executionPlan` (object)
- `inputNotes` (array)
- `methodAnalysis` (object)
- `mode` (string)
- `nameAnalysis`
- `nameSummary` (object)
- `noModelCalls` (boolean)
- `omittedItemsByKind` (object)
- `omittedTimelineYears` (integer)
- `publicationSideEffects` (boolean)
- `question` (string)
- `readingSummary` (object)
- `recommendations`
- `routes` (array)
- `sections` (object)
- `selection`
- `sources` (array)
- `timeline` (array)
- `unmatchedClaimIds` (array)
- `verdicts` (object)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/sihyeonjeon-legend-saju/legend-saju-mcp-production#diagnostics

## Score history

- 2026-09-21: 84
- 2026-09-20: 83
- 2026-09-19: 83
- 2026-09-18: 82
- 2026-09-17: 82
- 2026-09-16: 81
- 2026-09-15: 81
- 2026-09-14: 80
- 2026-09-13: 80
- 2026-09-12: 79
- 2026-09-11: 79
- 2026-09-10: 78
- 2026-09-09: 78
- 2026-09-08: 77
- 2026-09-07: 77
- 2026-09-06: 77
- 2026-09-05: 76
- 2026-09-04: 76
- 2026-09-03: 75
- 2026-09-02: 75
- 2026-09-01: 74
- 2026-08-31: 74
- 2026-08-30: 73
- 2026-08-29: 73
- 2026-08-28: 72
- 2026-08-27: 72
- 2026-08-26: 71
- 2026-08-25: 69
- 2026-08-24: 69
- 2026-08-23: 64

## Common questions

### What is the Legend Saju MCP server?

Legend Saju is an MCP server listed in the public MCP registry as io.github.SihyeonJeon/legend-saju. Source-traceable Saju, Zi Wei, Qimen, Daliuren, Tieban, naming, and related calculations. This page covers its hosted endpoint (https://legend-saju-mcp-production.up.railway.app/mcp).

### Is the Legend Saju MCP server safe to use?

Legend Saju scores 84 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Legend Saju MCP server expose?

Legend Saju exposes 13 tools: legend_saju_manifest, legend_saju_capabilities, legend_saju_read_fortune, legend_saju_analyze_compatibility, legend_saju_select_dates, and 8 more. Their descriptions and schemas cost roughly 3,102 tokens of context every time the server is loaded.

### Does the Legend Saju MCP server require authentication?

No. We connected to Legend Saju without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Legend Saju MCP server still maintained?

Legend Saju is still listed as active in the MCP registry. We last reached this channel on 21 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://legend-saju-mcp-production.up.railway.app/mcp
- Repository: https://github.com/SihyeonJeon/legend-saju
- Changelog RSS feed: https://verifymcp.io/servers/sihyeonjeon-legend-saju/legend-saju-mcp-production.xml
- Changelog JSON feed: https://verifymcp.io/servers/sihyeonjeon-legend-saju/legend-saju-mcp-production.json
- HTML version of this page: https://verifymcp.io/servers/sihyeonjeon-legend-saju/legend-saju-mcp-production