Server data from the Official MCP Registry
Divination for AI agents: Hafez, Tarot, I Ching, Runes, Geomancy, and the five-oracle Council.
About
Divination for AI agents: Hafez, Tarot, I Ching, Runes, Geomancy, and the five-oracle Council.
Remote endpoints: streamable-http: https://mcp.spiritwavelabs.com/mcp
Security Report
Valid MCP server (2 strong, 2 medium validity signals). No known CVEs in dependencies. Imported from the Official MCP Registry.
6 tools verified · Open access · No issues found
Security scores are indicators to help you make informed decisions, not guarantees. Always review permissions before connecting any MCP server.
Permissions Required
This plugin requests these system permissions. Most are normal for its category.
How to Connect
Remote Plugin
No local installation needed. Your AI client connects to the remote endpoint directly.
Add this to your MCP configuration to connect:
{
"mcpServers": {
"io-github-vizkr-council": {
"url": "https://mcp.spiritwavelabs.com/mcp"
}
}
}Documentation
View on GitHubFrom the project's GitHub README.
SpiritWave Labs — Pentamancy Council MCP Server
Exposes the SpiritWave Labs Pentamancy Council (five-oracle divination engine) to AI agents via the Model Context Protocol.
Tools
consult_council
Consults five ancient oracles in parallel and synthesizes their readings into a single unified counsel:
- Hafez — Persian Sufi poetry (Fal-e Hafez)
- Tarot — Rider-Waite 78-card deck, 3-card spread
- Runes — Elder Futhark, 3-rune draw
- I Ching — Book of Changes, coin-cast hexagram
- Geomancy — Arabic `Ilm al-Raml, shield chart
The server draws all five, interprets each, then synthesizes. Best for questions of substance — major decisions, emotional crossroads, spiritual direction.
Input: { question: string } (3–1000 chars)
Individual consultations
consult_hafez, consult_tarot, consult_iching, consult_runes, consult_geomancy — each draws its own tradition server-side and interprets it in that tradition's voice. The tool descriptions are written so agents route themselves; there is deliberately no router tool.
Payments (x402)
Paid from day one. $0.50 per Council reading, $0.10 per individual oracle, in USDC on Base via the x402 protocol:
initialize,tools/list, notifications — free. Connect, discover, read the prices.tools/callon a paid tool without payment → HTTP 402 withpaymentRequirementsin the body (schemeexact, payee address, atomic amount).- Retry with the
X-PAYMENTheader (signed EIP-3009 payload); the x402 Foundation facilitator verifies and settles, the call proceeds, and the settlement receipt returns inX-PAYMENT-RESPONSE.
Agents using x402-fetch (or any x402-aware client) get this flow automatically. Configuration: X402_PAYEE, X402_FACILITATOR, X402_ENABLED (see docker-compose.yml).
Architecture
This is a thin proxy. The MCP server receives JSON-RPC tool calls and forwards them to the existing SpiritWave Labs PHP API:
Agent → MCP server (this repo, Streamable HTTP) → PHP API (temple.php, individual oracle endpoints) → DeepSeek
The divination engine lives entirely in the PHP backend. This server adds the MCP protocol layer — it does not implement any divination logic itself.
Transport
Streamable HTTP (the MCP standard for remote servers). Single endpoint: POST /mcp.
Setup
npm install
npm run build # compile TypeScript
npm start # run the compiled server
# or for development:
npm run dev # run via tsx with hot reload
Configuration
| Env var | Default | Description |
|---|---|---|
PORT | 3001 | HTTP port |
SWL_API_BASE | https://spiritwavelabs.com | The PHP API base URL to proxy to |
Roadmap
- Phase 1 (done): MCP scaffold, six tools, deployed at
mcp.spiritwavelabs.com(Docker, behind nginx, healthy since 2026-08-18). - Phase 2: x402 payment layer — per-call USDC payment via Coinbase CDP facilitator (Base network). Agents pay per reading.
- Phase 3: Registry listing — official MCP Registry, Smithery, Glama.
License
MIT © SpiritWave Labs
Reviews
No reviews yet
Be the first to review this server!
More Developer Tools MCP Servers
Fetch
Freeby Modelcontextprotocol · Developer Tools
Web content fetching and conversion for efficient LLM usage
Git
Freeby Modelcontextprotocol · Developer Tools
Read, search, and manipulate Git repositories programmatically
Toleno
Freeby Toleno · Developer Tools
Toleno Network MCP Server — Manage your Toleno mining account with Claude AI using natural language.
mcp-creator-python
Freeby mcp-marketplace · Developer Tools
Create, build, and publish Python MCP servers to PyPI — conversationally.
MarkItDown
Freeby Microsoft · Content & Media
Convert files (PDF, Word, Excel, images, audio) to Markdown for LLM consumption
MCP Marketplace
Freeby mcp-marketplace · Developer Tools
Search and install MCP servers from inside your AI client.
