This server provides six Chinese metaphysics engines as MCP tools, enabling AI-powered divination and destiny analysis across multiple classical traditions:
BaZi Analysis (ming_bazi_analyze): Compute a full BaZi (Four Pillars) chart given a birth date, gender, optional birth hour, and location — returns Day Master analysis, pattern classification (格局), decade luck pillars (大运), and annual outlook.
Qi Men Dun Jia Direction Reading (ming_qmdj_direction): Get optimal directions, best timing windows, and strategic framing for a specific date and intention using classical QMDJ.
Zi Wei Dou Shu Natal Chart (ming_zwds_chart): Generate a twelve-palace natal chart with starred positions, 四化 transformations, and palace-focused narrative for domains like career, wealth, marriage, and health.
Feng Shui Flying Stars & Kua Analysis (ming_fengshui_flying_stars): Calculate Kua number, Eight Mansions directional analysis, and annual Flying Star map (年飛星) for any year between 1700–2100, with favorable/unfavorable directional guidance.
I Ching Hexagram Casting (ming_iching_cast): Cast a hexagram using the classical 納甲法 (Liu Yao method) for a specific question, returning the hexagram, changing lines, transformed hexagram, and interpretation.
Integrated Five-Engine Forecast (ming_full_forecast): Run all four birth-data engines (BaZi + ZWDS + Feng Shui + QMDJ) together to produce a unified forecast focused on a specific domain (wealth, career, health, relationship, or general) for a target year.
Click on "Install 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., "@ming-metaphysics-mcp Analyze BaZi for 1990-03-15 male Singapore"
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.
Five Chinese metaphysics engines as MCP tools for Claude Desktop and any MCP-compatible client.
bazi-mcpDimension | Cantian | Ming |
Arts covered | BaZi only | All five — BaZi + QMDJ + ZWDS + Feng Shui + I Ching |
Engine depth | Good BaZi implementation | 9.0–9.5/10 expert-verified across all five engines |
Classical sourcing | Not documented | 子平真詮, 淵海子平, 紫微斗數全書 + 108-title library cited |
Output quality | Competent readings | Scholar-validated, bilingual (EN/ZH), report-grade depth |
Consultation funnel | None | Master reading available via Ming Bot (link TBA) |
Kua + Eight Mansions | ❌ | ✅ |
QMDJ timing | ❌ | ✅ (sxtwl Ju computation) |
I Ching (Liu Yao) | ❌ | ✅ (classical 納甲法) |
Related MCP server: taibu
Tool | Engine | Description |
| BaZi 八字 | Four Pillars chart — Day Master, pattern, luck pillars |
| QMDJ 奇門 | Optimal direction + timing window for a date |
| ZWDS 紫微 | Twelve-palace natal chart with 四化 transformations |
| Feng Shui 風水 | Kua number + Eight Mansions directional analysis |
| I Ching 易經 | Hexagram via classical 納甲法 (Liu Yao) |
| All four birth-data engines | Integrated five-engine forecast with confidence score |
This package is an MCP wrapper. It does not contain metaphysics
calculation logic — it forwards tool calls to a Ming engine endpoint over
HTTP. To use it, point MING_API_URL at a running engine.
Two ways to get an engine:
Hosted endpoint (preferred, when available). A public Ming endpoint
will be announced; once available, configure MING_API_URL to point at
it and you're done.
Self-host. The Ming engine itself is currently a closed-source
reference implementation. If you have access to the Ming codebase, run
uvicorn api.main:app --port 8000 and point this MCP at localhost:8000.
Without a reachable engine, the MCP server starts and lists tools, but tool calls return an HTTP error.
See "Engine requirement" above.
npm install -g @espivc/ming-metaphysics-mcpclaude_desktop_config.jsonmacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"ming": {
"command": "ming-metaphysics-mcp",
"args": [],
"env": {
"MING_API_URL": "http://localhost:8000"
}
}
}
}Restart Claude Desktop. The Ming tools will appear in the tools list.
In Claude Desktop:
Using the ming_bazi_analyze tool, analyze the chart for someone born 1990-03-15, male, in Singapore.You should get a full BaZi reading. If the tool errors, verify the Python engine is running at port 8000.
The following capabilities require FastAPI expansion before they fully function as specified. Each is flagged with a note in the tool response — no silent failures.
Gap | Affected Tool | Required FastAPI Change |
Annual flying star map for a specific year |
|
|
|
|
|
Full ISO casting_timestamp |
|
|
| All individual tools | The spec assumed |
To implement year-specific flying stars or forecast_year support, add those parameters to /consult in api/main.py and update the corresponding tool handlers here.
git clone <this-repo>
cd ming-metaphysics-mcp
npm install
npm run build # compile TypeScript → dist/
npm test # smoke tests (no engine required)
# With engine running at localhost:8000:
npx ts-node scripts/benchmark.ts --tool all --iterations 5Variable | Default | Description |
|
| Base URL of the Ming FastAPI engine |
Tool | Target |
| < 3s |
| < 3s |
| < 3s |
| < 5s |
| < 5s |
| < 3s |
If any tool exceeds 5s consistently, check the engine bottleneck and consider adding timeout: 10000 to the MCP config.
None at the wrapper level — this server is open-source and free (MIT
license). Authentication, if any, is enforced by whatever endpoint
MING_API_URL points at.
A guided five-engine consultation (BaZi + ZWDS + QMDJ + Feng Shui + I Ching synthesised by Master Chen) is available via Ming's Telegram bot. Link will be published once the bot is in public beta.
This MCP wrapper itself does not collect data. It forwards your tool
arguments (birth date, hour, gender, question text) to whichever
MING_API_URL you configured. If you point at a hosted endpoint, that
endpoint receives the data — read its privacy policy. If you self-host,
nothing leaves your network.
Birth data is sensitive. If you're configuring this for end users, be explicit about which endpoint receives their inputs.
This package is at version 1.0.0. The MCP protocol surface (6 tools, JSON
schemas, response shapes) is stable. The underlying Ming engine evolves
faster — minor numeric changes in tool responses are normal.
Contributions welcome — see CONTRIBUTING.md.
MIT — see LICENSE.
Compute a full BaZi (Four Pillars of Destiny 八字) chart. Returns Day Master analysis, pattern classification (格局), decade luck pillars (大运), and annual outlook. Engine verified against 子平真詮 and 淵海子平. Requires Ming engine running at MING_API_URL.
| Name | Required | Description | Default |
|---|---|---|---|
| birth_date | Yes | Date of birth in YYYY-MM-DD format. Must be after 1900-01-01. | |
| birth_hour | No | Hour of birth in 24-hour format (0–23). If unknown, omit — analysis will note the limitation. | |
| birth_location | No | City and country of birth (e.g. 'Singapore, Singapore'). Provides timezone context. | |
| gender | Yes | Gender determines luck pillar direction (forward for males in yang years, backward for females). | |
| question | No | Optional. Specific question to orient the reading (e.g. 'Is 2026 good for a career change?'). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description carries full burden. It discloses the compute behavior, output types, and engine verification. It does not mention destructive actions or permissions, but for a read-only computation tool, the behavioral transparency is adequate and adds value beyond the schema.
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 three sentences (∼50 words), each serving a purpose: stating the main action and outputs, verifying accuracy, and noting a requirement. No redundant or extraneous information.
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?
The tool has 5 parameters (2 required) and no output schema. The description provides high-level output categories and verification context, which is helpful. However, it does not detail the output structure or error handling, so completeness is slightly lacking.
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?
Schema description coverage is 100%, so the baseline is 3. The description does not add significant meaning beyond what the schema already provides for each parameter. It mentions the engine requirement but not parameter-specific details.
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 uses a specific verb 'Compute' with a clear resource 'BaZi chart'. It lists exact outputs and references verification against authoritative sources. Sibling tools are distinct (fengshui, forecast, iching, etc.), so differentiation is clear.
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 states it requires the Ming engine running at MING_API_URL, providing a prerequisite. It does not explicitly state when not to use or compare with siblings, but given the distinct domains of siblings, the usage context is clear and no explicit exclusions are critical.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Compute the Kua number (卦命), directional analysis, and annual Flying Star map (年飛星) for a person. Returns Kua group, favorable/unfavorable directions per Eight Mansions (八宅法), the nine-palace annual star chart for the requested year, and a five-engine directional synthesis.
| Name | Required | Description | Default |
|---|---|---|---|
| year | Yes | Year for the annual Flying Star map (年飛星). Range 1700–2100. Defaults to current year when omitted. | |
| birth_date | Yes | Date of birth in YYYY-MM-DD format — used to compute the Kua number. | |
| gender | Yes | Gender is required for Kua number calculation. | |
| location_description | No | Optional. Description of the property (e.g. 'apartment, front door faces North'). |
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 describes the computational outputs but does not disclose behavioral traits such as accuracy assumptions, required expertise, or rate limits.
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 two sentences, front-loading the main purpose. It lists outputs efficiently, though a more structured format (e.g., bullet points) could improve clarity.
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?
No output schema exists, so the description must hint at return format. It lists all major outputs (Kua group, directions, chart, synthesis), which is adequate for an agent to understand the return value, though format details are missing.
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?
Schema coverage is 100%, so baseline is 3. The description adds meaning by explaining the purpose of each parameter (e.g., year for annual star map, birth_date for Kua calculation), which is beyond the schema's type and format details.
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 explicitly states the tool computes Kua number, directional analysis, and annual Flying Star map, listing specific outputs (Kua group, directions, chart, synthesis). This distinguishes it from siblings like ming_bazi_analyze and ming_qmdj_direction.
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 does not provide explicit guidance on when to use this tool versus alternatives. While the listed outputs imply a feng shui context, no direct comparison or exclusion is given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Run all four birth-data engines (BaZi + ZWDS + Feng Shui + QMDJ) for a birth profile and return an integrated Master-tier forecast. I Ching is excluded from bulk forecasts (it requires a specific question — use ming_iching_cast separately).
| Name | Required | Description | Default |
|---|---|---|---|
| birth_date | Yes | Date of birth in YYYY-MM-DD format. | |
| birth_hour | No | Hour of birth in 24-hour format (0–23). | |
| birth_location | No | City and country of birth (e.g. 'Singapore, Singapore'). | |
| gender | Yes | ||
| forecast_year | No | The year to forecast for. Range 1900–2200, defaults to current year. Affects BaZi luck pillar selection and ZWDS 流年四化 annual chart. | |
| question | No | Primary question to orient the synthesis (e.g. 'Is 2026 the right year to start a business?'). | |
| goal | No | Focus domain for the synthesis. Maps to the /consult 'goal' parameter. Defaults to 'general'. | general |
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 only states it 'runs' the engines, without disclosing behavioral traits like read-only status, side effects, or permissions. Minimal transparency for a complex tool.
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?
Two sentences, front-loaded with the main purpose, and the second sentence adds a crucial usage note. No unnecessary words.
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?
For a complex tool integrating four engines without an output schema, the description is too minimal. It does not explain what 'integrated Master-tier forecast' includes, nor any behavioral assumptions or expected output structure.
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?
Schema coverage is high (86%), so the schema already documents all parameters. The description adds context about I Ching exclusion but does not significantly enhance parameter meaning. Baseline 3 is appropriate.
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 it runs four engines (BaZi, ZWDS, Feng Shui, QMDJ) and returns an integrated forecast. It distinguishes from siblings by explicitly excluding I Ching and directing to ming_iching_cast.
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?
It provides clear context for when to use (integrated forecast) and explicitly excludes I Ching, directing to a sibling. However, it lacks guidance on when to use this versus individual engine tools like ming_bazi_analyze.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Cast an I Ching (易經) hexagram using the classical 納甲法 (Liu Yao method). Returns the hexagram, changing lines, transformed hexagram, and interpretation. The casting derives from the current date/time (SGT) by default.
| Name | Required | Description | Default |
|---|---|---|---|
| question | Yes | The specific question to cast for. Must be a genuine question about a real situation. Example: 'Should I accept the offer from Company X?' — not 'What will happen to the economy?' | |
| casting_timestamp | No | Optional. ISO 8601 timestamp of the casting moment (e.g. '2026-04-18T14:30:00'). When provided, the date and time are both forwarded to the engine — the time component determines the hour branch (地支) used for 納甲 analysis. If omitted, uses the server's current SGT time. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the burden. It mentions that casting derives from current date/time by default and that the optional timestamp affects the hour branch. However, it does not explicitly state that the operation is read-only (non-destructive) or any limitations. Adequate but not thorough.
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 only two sentences, gets straight to the point, and front-loads the main purpose. Every sentence adds essential information 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 has 2 parameters and no output schema, the description covers the return elements (hexagram, changing lines, etc.) and the default behavior with date/time. It could elaborate on the interpretation output, but overall it provides sufficient context for a divination 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?
The input schema already has good descriptions (100% coverage). The description adds value by emphasizing that the question must be genuine and about a real situation, and by explaining how the timestamp's time component affects the analysis. This enhances the schema's information.
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 casts an I Ching hexagram using the classical nàjiǎ method, and specifies the output includes hexagram, changing lines, transformed hexagram, and interpretation. This is specific and distinguishes it from sibling tools like bazi or fengshui.
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?
No explicit guidance on when to use this tool versus alternatives like ming_bazi_analyze or ming_fengshui_flying_stars. The description gives an example of question format but does not explain when I Ching is appropriate compared to other divination systems.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Compute a Qi Men Dun Jia (奇門遁甲) reading for a specific date. Returns the optimal direction, best timing windows, lead star, and strategic framing. Ju number computed via sxtwl solar term library for classical accuracy.
| Name | Required | Description | Default |
|---|---|---|---|
| date | No | Date for the QMDJ reading in YYYY-MM-DD format. Defaults to today (SGT) if omitted. | |
| hour | No | Optional hour for hour-level resolution. If omitted, returns the best hour block for the day. | |
| question | Yes | The specific intention (e.g. 'Best direction for a job interview', 'Is today favourable for signing a contract?'). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must convey behavioral traits. It mentions the use of 'sxtwl solar term library for classical accuracy', adding technical transparency. However, it does not disclose whether the operation is idempotent, safe (read-only), or any error conditions. The description is adequate but not comprehensive.
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?
Two sentences, no wasted words. The first sentence states purpose and outputs, the second adds technical detail. Information is front-loaded and easy to parse.
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?
No output schema exists, so the description covers the key return values (optimal direction, timing windows, lead star, strategic framing). For a complex divination tool, this provides a good overview. Minor gap: no mention of error handling or edge cases (e.g., invalid date), but overall sufficient for an agent to understand the output.
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?
Input schema has 100% description coverage, so the schema itself documents the parameters well. The description provides minimal additional meaning beyond the schema, only reiterating that omitted hour returns best hour block. Since schema coverage is high, baseline 3 is appropriate.
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 computes a Qi Men Dun Jia reading for a specific date and lists specific outputs (optimal direction, best timing windows, lead star, strategic framing). The verb 'Compute' and resource 'reading' are specific, and the tool name 'direction' aligns with the main output, differentiating it from sibling tools that focus on other Ming methods.
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 implies use when a QMDJ reading is needed for a date, but lacks explicit guidance on when to use this tool versus siblings like 'ming_bazi_analyze' or 'ming_fengshui_flying_stars'. No exclusions or alternatives are mentioned, leaving the agent to infer context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Compute a Zi Wei Dou Shu (紫微斗數) twelve-palace natal chart. Returns palace highlights, starred positions, 四化 transformations, and synthesis for a specific question domain. Verified against 紫微斗數全書.
| Name | Required | Description | Default |
|---|---|---|---|
| birth_date | Yes | Date of birth in YYYY-MM-DD format. | |
| birth_hour | Yes | Hour of birth (0–23). Required for accurate palace placement — Zi Wei palace positions shift by birth hour. | |
| birth_location | No | City and country of birth. Used for timezone context. | |
| gender | Yes | Gender affects 四化 (sihua) transformation assignments. | |
| focus_palace | No | Optional. Focus the narrative on this palace. If omitted, returns highlights across all twelve. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description should clarify behavioral traits. It states the tool 'computes' and 'returns' data, implying no side effects, but does not explicitly state read-only status, auth requirements, or limitations. The verification claim adds trust but not behavioral transparency.
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 highly concise (two sentences) and front-loaded with the core action. Every word adds value: computes, returns specific items, verification.
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?
Despite the complexity of ZWDS, the description outlines key output categories but does not specify output format or structure. Without an output schema, more detail on the return value (e.g., narrative vs. structured data) would improve completeness.
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?
All five parameters have descriptions in the input schema (100% coverage), so the description adds no extra semantic value. The tool description mentions 'specific question domain' which vaguely relates to the optional focus_palace parameter but does not elaborate.
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 computes a ZWDS natal chart and lists specific outputs (palace highlights, starred positions, 四化). The mention of verification against 紫微斗數全書 adds credibility. While sibling tool names are diverse, the description does not explicitly contrast with them, but the technical specificity makes its purpose unambiguous.
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 provides no guidance on when to choose this tool over sibling tools. It does not state prerequisites, exclusions, or complementary use cases.
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.
v1.0.0ming_bazi_analyzeming_fengshui_flying_starsming_full_forecastming_iching_castming_qmdj_directionming_zwds_chartScored across 6 tools
Each tool covers a distinct metaphysical system (BaZi, Feng Shui, I Ching, QMDJ, ZWDS) plus a combined forecast, with no overlapping purposes.
All tools follow a consistent 'ming_system_action' pattern in snake_case, e.g., ming_bazi_analyze, ming_iching_cast.
With 6 tools covering the main systems of Chinese metaphysics, the count is well-scoped and appropriate for the server's purpose.
The tool set covers all major Chinese metaphysical systems (BaZi, ZWDS, QMDJ, Feng Shui, I Ching) and includes a combined forecast, leaving no obvious gaps.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
BaZi (八字) MCP gateway + 玄学社区. 12 tools (4 fortune + 5 forum + 3 meta). x-api-key required.
Chinese metaphysics (bazi, qimen, 5-element) as decision-support tools for AI agents.
BaZi four pillars, Chinese zodiac, lunisolar calendar and almanac days for AI agents.
Read-only Bazi, True Solar Time, and Chinese almanac tools in English and Traditional Chinese.
