io.github.douglasganPublished by GitHub account douglasganv0.3.3Updated Oct 24, 2026
Chinese metaphysics (bazi, qimen, 5-element) as decision-support tools for AI agents.
AskTian exposes Chinese metaphysics (bazi, five elements, daily 干支 energy) as tools so an assistant can give daily readings, compatibility checks and timing…
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/io.github.douglasgan%2Fasktian/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.Add this to your client's mcpServers config.
{
"mcpServers": {
"asktian": {
"type": "http",
"url": "https://mcp.asktian.com/mcp"
}
}
}[CI] [npm] [License: MIT] [asktian MCP server]
Chinese metaphysics inside your AI assistant. 不知道就问天 · Ask tian when you don't know.
Adds 4000 years of Chinese metaphysical traditions (bazi / 八字, qimen / 奇门, five elements, daily 干支 energy) as callable tools for any AI agent that speaks the Model Context Protocol — Claude Desktop, Claude Code, Cursor, Windsurf, Zed, and any MCP-compatible client.
When you ask your AI assistant a timing, person, or decision question, it can quietly consult asktian before answering.
The decision layer for AI agents. Agents already plug in search, memory, and payments — askTIAN is the layer that gives them a stance: a specific, falsifiable call instead of "it depends." → Why it sells · 2-min quickstart
✨ Real readings, no key needed.
The tools call the live askTIAN backend and return real results — daily almanac, fate compatibility, name analysis, day energy — straight out of the box. The read endpoints are public and rate-limited (~300 requests / 15 min). An optional
ASKTIAN_API_KEY(api.asktian.com) raises the limit and unlocks the premiumtian.*reading tier.market_readis a deterministic local novelty signal;best_timereturns a guided preview (no backend endpoint yet).
Then add to your client's MCP config:
Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
Restart Claude Desktop. Look for the 🔌 icon — asktian should appear with 6 tools.
Add to ~/.cursor/mcp.json:
Add to ~/.codeium/windsurf/mcp_config.json — same shape as above.
Add to your Zed settings under assistant.mcp_servers — same command + env.
Run asktian-mcp as a subprocess; it speaks JSON-RPC over stdio per the MCP spec.
For LangChain, LlamaIndex, Fetch.ai, or any agent that connects to a hosted MCP endpoint, run the server in HTTP mode instead of stdio:
Hosted at https://mcp.asktian.com/mcp. Pass your key as a Bearer header:
Authorization: Bearer YOUR_ASKTIAN_API_KEY.
Both have native MCP adapters — askTIAN works with zero integration code. Copy-paste snippets in docs/langchain-llamaindex.md.
The key is optional — readings are real either way.
To use a key (higher limits + premium tier), set ASKTIAN_API_KEY in your client config:
Hosted (streamable-HTTP)? Pass it as a header instead: Authorization: Bearer at_live_....
asktian_daily_readingPersonalized daily energy reading for a person.
Use when: user asks how today will be, what colors to wear, what direction to face their desk, daily guidance.
asktian_compatibilityFate compatibility between two people. Returns qualitative label first (e.g. "互补型 Complementary"), then numeric score (hidden if <60 per asktian design principles — low compat should never feel like rejection).
Use when: "will this person and I work", "compatibility check", "is this a good match".
asktian_best_time_for_actionThe killer tool. Find the most auspicious time windows for a specific action over the next N days.
Use when: "when should I do X", "should I move this meeting", "is tomorrow a good day to launch", "when should I have the hard talk".
asktian_today_energyGeneral energy of the day — no birthdate needed.
Use when: AI wants to add cosmic context to a generic suggestion without needing the user's birthdate.
asktian_name_analysisQuick energetic profile of a name (姓名学).
Use when: discussing baby names, company names, or "what kind of person is X" when birthdate unknown.
asktian_market_readA Chinese-metaphysics signal on a binary prediction-market question (Polymarket/Kalshi style).
Use when: a user or a trading agent wants an uncorrelated, for-fun read on a market — "will X happen by date Y". The value isn't prediction; it's a deterministic signal that doesn't read the same news every LLM reads, published so the calls can be scored over time. ⚠️ Entertainment / falsifiable ritual — NOT financial advice. Every response says so, and the tool is built to be presented as a novelty, never as a bet recommendation.
asktian is opinionated. The MCP tools surface these constraints to your AI agent through the note_for_ai field on each response. Notable rules:
If your AI client surfaces a numeric score when should_show_score: false, it's violating the design contract.
These are the kinds of user prompts that an AI agent with asktian installed handles dramatically better:
The agent's response in each case becomes specific and actionable instead of vague.
PRs welcome. The lib/ folder is intentionally self-contained for clean npm distribution.
MIT — use it anywhere, fork it, ship it inside your own product. The asktian protocol is meant to be public infrastructure.
不知道就问天.
Source: README.md at commit 0c6b219
Get today's personalized Chinese metaphysics (八字 bazi + 干支 daily energy) reading for a person. Returns their archetype (one of 8 trigrams 八卦), today's energy, favorable colors/direction/hours, headline advice, and any caution. Use this when the user asks how today will be for them, what colors to wear, where to face their desk, or for general daily guidance.
genderbirthdaterequiredbirth_hourCompute fate compatibility between two people via Chinese metaphysics (八字 pairing, 5-element generation/clash). Returns qualitative label first (e.g. '互补型 Complementary'), then a numeric score (hidden if <60 to avoid making low-compat feel like rejection — this is intentional per the asktian design principles). Useful when user asks about compatibility, fit, or 'will this person and I work'.
dimensionperson_a_birthdaterequiredperson_b_birthdaterequiredFind the most auspicious time windows in the next N days for a specific action. Use this when the user asks 'when should I do X', 'should I move this meeting', 'is tomorrow a good day to launch', 'when should I have the hard conversation', etc. Returns top 3 best windows and any windows to avoid. This is the most useful tool for real-time decision support inside any AI assistant — it lets you give specific scheduling advice instead of vague reflections.
actionbirthdaterequiredrange_daysGet today's GENERAL energy (no person needed) — the 干支 (stem + branch) and the dominant 5-element character of the day. Useful when the user asks 'what kind of day is it', 'what's the energy today', or when an AI agent wants to add cosmic context to a generic suggestion without needing the user's birthdate.
dateQuick energetic profile of a name (姓名学 name-analysis). Useful when the user asks about someone's name, a baby name, a company name, or 'what kind of person is X' when no birthdate is available. Returns a one-line vibe + dominant element guess.
namerequiredlanguageGet a Chinese-metaphysics signal on a binary prediction-market question (Polymarket/Kalshi style yes/no outcomes). Use when a user — or a trading agent — wants an UNCORRELATED, for-fun read on a market: 'will X happen by date Y'. Returns a lean (yes/no/neutral), a confidence, the 五行 reasoning from the resolution date's energy, and a mandatory disclaimer. This is ENTERTAINMENT and a falsifiable ritual — NOT financial advice. Always present it as a novelty signal, never as a recommendation to place a bet.
questionrequiredresolve_datesubject_birthdate100% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
You: "I have a hard conversation with my boss tomorrow at 3pm. Should I move it?"
Claude (with asktian MCP): → calls asktian_best_time_for_action({ birthdate, action: "difficult_conversation" }) → "Friday 10am scores much higher. Tomorrow 3pm is your clash hour. Want me to draft a message to reschedule?"npm install -g @asktian/mcp-server{ "mcpServers": { "asktian": { "command": "asktian-mcp", "env": { "ASKTIAN_API_KEY": "at_live_xxxxxxxxxxxxxxxx" } } }}{ "mcpServers": { "asktian": { "command": "asktian-mcp", "env": { "ASKTIAN_API_KEY": "at_live_xxxxxxxxxxxxxxxx" } } }}ASKTIAN_MCP_HTTP=1 PORT=8080 npx -y @asktian/mcp-server# → streamable-HTTP on :8080/mcp (health check: GET :8080/health){ "mcpServers": { "asktian": { "command": "npx", "args": ["-y", "@asktian/mcp-server"], "env": { "ASKTIAN_API_KEY": "at_live_..." } // ← omit this line to stay in local mode } }}input: { birthdate: "1992-05-15", birth_hour?: "14:30", gender?: "male"|"female"|"any" }output: archetype (one of 8 trigrams), today's stem-branch energy, favorable colors / direction / hours, headline + body adviceinput: { person_a_birthdate, person_b_birthdate, dimension?: "love"|"career"|"friend"|"general" }output: qualitative label, category, element flow, today's advice, score (with should_show_score flag)input: { birthdate, action: "difficult_conversation"|"negotiation"|"launch"|... , range_days?: 7 }output: top 3 best windows (date + hour + score + reason), windows to avoidinput: { date?: "YYYY-MM-DD" } (defaults to today)output: 干支 stem+branch, dominant 5-element character, descriptioninput: { name, language?: "en"|"zh"|"auto" }output: dominant element guess, tone, one-linerinput: { question, resolve_date?: YYYY-MM-DD, subject_birthdate?: YYYY-MM-DD }output: { signal: { lean: yes|no|neutral, score 5–95, confidence }, reasoning, disclaimer }