Turtle Noir
MCP server for Turtle Soup (lateral thinking puzzles). Start sessions, ask questions, get 4-class judgments (Yes/No/Both/Irrelevant), and reveal the full story when allowed.
mcp-turtle-noir
MCP server for Turtle Soup (lateral thinking puzzles).
This package is a thin MCP layer over Turtle Noir backend APIs and is designed for stdio transport.
Features
start_session: start a new puzzle sessionask_question: ask one question and receive a structured resultgive_up_and_reveal: reveal the solution (subject to backend reveal policy)- Multilingual MCP output (
zh-CN,en-US,ja-JP) vialanguage - Keeps puzzle solutions on the backend during normal gameplay
Transport
- Supported:
stdio - Not included in this package: SSE/HTTP MCP transport
Requirements
- Node.js 18+
Install and Run
npx -y mcp-turtle-noir
MCP Client Config
{
"mcpServers": {
"turtle-noir": {
"command": "npx",
"args": [
"-y",
"mcp-turtle-noir"
]
}
}
}
With environment variables:
{
"mcpServers": {
"turtle-noir": {
"command": "npx",
"args": [
"-y",
"mcp-turtle-noir"
],
"env": {
"TURTLE_NOIR_API_BASE_URL": "https://turtlenoir.com/api/mcp",
"TURTLE_NOIR_API_TIMEOUT_MS": "10000",
"TURTLE_NOIR_API_KEY": "YOUR_API_KEY"
}
}
}
}
Tools
1) start_session
Input (all optional):
{
"region": "US",
"keyword": "island",
"language": "en-US"
}
Output:
{
"session_id": "...",
"puzzle_id": "...",
"title": "...",
"content": "...",
"language": "en-US",
"instruction": "...",
"translation_instruction": "..."
}
2) ask_question
Input:
{
"session_id": "...",
"question": "...",
"language": "en-US"
}
Output:
{
"session_id": "...",
"language": "en-US",
"answer_key": "irrelevant",
"answer": "Irrelevant",
"answer_original": "...",
"short_reason": "...",
"solved": false,
"progress": 35,
"translation_instruction": "..."
}
3) give_up_and_reveal
Input:
{
"session_id": "...",
"language": "en-US"
}
Output:
{
"session_id": "...",
"language": "en-US",
"title": "...",
"solution": "...",
"cta_url": "https://turtlenoir.com",
"cta_text": "...",
"translation_instruction": "..."
}
Note: backend may reject reveal if progress is below a threshold (for example progress < 60).
Environment Variables
TURTLE_NOIR_API_BASE_URL(default:https://turtlenoir.com/api/mcp)TURTLE_NOIR_API_TIMEOUT_MS(default:10000)TURTLE_NOIR_API_KEY(optional Bearer token)
Development
npm install
npm run build
node dist/index.js
Quick Start
See QUICKSTART.md.
Chinese Docs
See README.zh-CN.md.
License
MIT. See LICENSE.
Acknowledgements
- Official Website: Turtle Noir
- Chinese Mirror: 出前一汤
Похожие серверы
Topaz Labs Enhance
AI image enhancement (upscaling, denoising, sharpening) via the Topaz Labs cloud API.
CS2 RCON MCP
A server for managing Counter-Strike 2 servers using the RCON protocol.
recon-crypto-mcp
MCP server for AI agents to manage a self-custodial crypto portfolio (Aave, Compound, Morpho, Uniswap V3, Lido, EigenLayer) on Ethereum/Arbitrum/Polygon via Ledger + WalletConnect. Private keys never leave the device.
通胜 MCP 服务
Provides Chinese Tung Shing (almanac) data, including calendar conversions, auspicious activities, and traditional metaphysical elements.
ReNoUn MCP Server
Structural observability for AI conversations. Detects loops, stuck states, and convergence patterns across 17 channels without analyzing content.
Admit Coach — University Finder
Search 3,500+ US universities, estimate admission chances, check financial aid by income bracket, and build balanced college lists. Free MCP server, no API key required. Data from IPEDS and College Scorecard
Compeller
Create AI music videos and audio-reactive visuals from songs through MCP.
Mnemory
A self-hosted, secure, feature-rich memory system for AI agents and assistants. Provides intelligent fact extraction and deduplication, with an artifact store for detailed content.
MCP OCR Server
An MCP server for Optical Character Recognition (OCR) using the Tesseract engine.
Klavis Strata
One MCP server for AI agents to use any tools reliably at any scale