# AI Divination Skills

An MCP server that hands your agent audited scripts for tarot, I Ching, Xiao Liu Ren and Bazi. The model interprets the draw instead of making it up.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 6
- Author: sapuyou45-bit
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/sapuyou45-bit/oraclebone
- Updated: 2026-09-01
- HTML: https://affpapa.org/en/nevibecode/mcp/ai-divination-skills

## What it does

AI Divination Skills wires four systems into an agent: tarot, I Ching, Xiao Liu Ren and Bazi (Four Pillars). A local script produces the draw, the hexagram or the position; the model receives that JSON and reads it. The split is the whole point — the result does not come from the model's text.

The scripts live at `skills/tarot/scripts/draw.py`, `skills/iching/scripts/cast.py`, `skills/xiaoliuren/scripts/cast.py` and `skills/bazi/scripts/cast.py`. Each one prints JSON with metadata that shows which method was used. Real readings pull from system randomness; seeded mode exists for tests and repeatable demos. Bazi needs the optional `lunar-python` extra, so that skill stays dark until you add it.

Approximate modes emit a warning rather than passing themselves off as the traditional method. None of this proves divination works. It is a stricter workflow for symbolic reasoning, and if you want the same result twice in a test you have to pass a seed yourself.

## Requirements
- Needs: Python and uv (commands run via uvx)

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add ai-divination-skills -- uvx ai-divination-skills
```
uvx runs the command named after the package; if the README names another one, use uvx --from ai-divination-skills <command>

### Codex

**Platform CLI**
```bash
codex mcp add ai-divination-skills -- uvx ai-divination-skills
```
uvx runs the command named after the package; if the README names another one, use uvx --from ai-divination-skills <command>

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "ai-divination-skills": {
            "command": "uvx",
            "args": [
                "ai-divination-skills"
            ]
        }
    }
}
```
uvx runs the command named after the package; if the README names another one, use uvx --from ai-divination-skills <command>

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "ai-divination-skills": {
            "type": "stdio",
            "command": "uvx",
            "args": [
                "ai-divination-skills"
            ]
        }
    }
}
```
uvx runs the command named after the package; if the README names another one, use uvx --from ai-divination-skills <command>

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add ai-divination-skills uvx ai-divination-skills
```
uvx runs the command named after the package; if the README names another one, use uvx --from ai-divination-skills <command>

## When to use it
- get a tarot draw the model did not invent
- check an I Ching hexagram against the actual cast
- compute a Xiao Liu Ren position from numbers
- build a Bazi chart from a birth datetime
- reproduce a demo reading with a seed

## Example prompts
- Draw three tarot cards with reversals and interpret them
- Cast an I Ching hexagram with the yarrow method and explain it
- Build a Bazi chart from this birth datetime

## Similar
- [REA](https://affpapa.org/en/nevibecode/mcp/rea.md) — MCP server · ★ 392262
- [GitHub](https://affpapa.org/en/nevibecode/mcp/github.md) — MCP server · ★ 33989
- [Netdata](https://affpapa.org/en/nevibecode/mcp/netdata.md) — MCP server · ★ 81163
- [browser-use](https://affpapa.org/en/nevibecode/mcp/browser-use.md) — MCP server · ★ 119231
- [Codebase Memory](https://affpapa.org/en/nevibecode/mcp/codebase-memory.md) — MCP server · ★ 47577
- [mcp-server](https://affpapa.org/en/nevibecode/mcp/mcp-server.md) — MCP server · ★ 43902

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md