Turtle Noir MCP

Created By

Yuikij5 months ago

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.

# Games

# Puzzle

Overview Content Tools Comments

Overview

mcp-turtle-noir is an MCP server for Turtle Soup / Lateral Thinking Puzzles.

What it does

start_session: starts a new puzzle session
ask_question: returns a structured judgment for each question
give_up_and_reveal: reveals the full story (subject to backend reveal policy)
Multilingual output via language: zh-CN, en-US, ja-JP

Answer model

The host answers in 4 classes:

Yes
No
Both (yes and no, depends on interpretation)
Irrelevant

Why this design

Puzzle solutions stay on the backend during normal gameplay
Lightweight stdio MCP server, easy to install in Claude/Cursor
Built for agent workflows and reproducible tool calls

Install

npx -y mcp-turtle-noir

About

I built this tool based on my web games Turtle Noir (English version) and 出前一汤. Check them out for multiplayer modes and visual clues!

Try in Playground

Server Config

{
  "mcpServers": {
    "turtle-noir": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-turtle-noir"
      ]
    }
  }
}

Project Info

Created At

5 months ago

Updated At

5 months ago

Author Name

Yuikij

Star

Language

License

Recommend Servers

View All

GitLab

@modelcontextprotocol

GitLab API, enabling project management

a year ago

Baidu Map

@baidu-maps

百度地图核心API现已全面兼容MCP协议，是国内首家兼容MCP协议的地图服务商。

a year ago

Test

@modelcontextprotocol

test

7 months ago

MCP Advisor

@istarwyh

MCP Advisor & Installation - Use the right MCP server for your needs

TypeScript

a year ago

Sentry

@modelcontextprotocol

Retrieving and analyzing issues from Sentry.io

a year ago

Australia Payments Mcp

@junter1989k-ai

12 days ago

mcp-server-flomo MCP Server

@chatmcp

Write notes to Flomo

JavaScript

a year ago

Bahrain Payments Mcp

@junter1989k-ai

12 days ago

Lithuania Payments Mcp

@junter1989k-ai

12 days ago

Realdentalcosts Mcp

@tresor4k

Query verified 2026 US dental cost data from Real Dental Costs: average implant, veneer, braces and procedure prices for all 50 states and 206 cities, state-vs-state comparisons, and the composite US Dental Cost Index. Open data (CC BY 4.0, Zenodo DOIs). Every response includes the source and a reference URL. Pricing/market research, not medical advice. Data: https://realdentalcosts.com

12 days ago

Filesystem

Secure file operations with configurable access controls

a year ago

12 days ago

12 days ago

12 days ago

13 days ago

VC follow intelligence for AI agents. Track what top investors follow on X — detect new follows, convergence signals, and trending companies before they're announced.

7 days ago

Search1API

One API for Search, Crawling, and Sitemaps

a year ago

Croatia Payments Mcp

@junter1989k-ai

12 days ago

Time

@modelcontextprotocol

A Model Context Protocol server that provides time and timezone conversion capabilities. This server enables LLMs to get current time information and perform timezone conversions using IANA timezone names, with automatic system timezone detection.

5 months ago

Slack

@modelcontextprotocol

Channel management and messaging capabilities

a year ago

12 days ago

12 days ago

12 days ago

12 days ago

12 days ago

@modelcontextprotocol

AI image generation using various models

a year ago

Neon MCP Server

@neondatabase-labs

MCP server for interacting with Neon Management API and databases

TypeScript

a year ago

Qiniu MCP Server

@Qiniu

基于七牛云产品构建的 Model Context Protocol (MCP) Server，支持用户在 AI 大模型客户端的上下文中通过该 MCP Server 来访问七牛云存储资源、利用 Dora 服务进行图片操作等。如果有什么需求欢迎在下方评论，您也可以在 github 仓库中提 issue。

Python

a year ago

Framesail AI

@framesail

Official remote MCP server for Framesail AI. Create long-form (faceless YouTube) videos end to end from any MCP client: script, locked character references, storyboard, voiceover, and final video editing — with characters and style held consistent across every shot. Making long-form AI video today means 8+ tabs stitched by hand — an LLM for the script, a voice model, an image model, a video model — with characters drifting between tools and style resetting at every export. Framesail replaces the patchwork: the whole pipeline runs in one place and manages your video's context end to end. Six stages: Style (paste images, videos, or YouTube links and Framesail reverse-engineers the look, voice, and direction), Script (write it yourself or generate it in your narrative style), Reference images (auto-generated for every character, place, and prop), Voiceover (one narrator or many characters, with word-level timing), Storyboard (planned scene by scene), and Editor (captions, music, SFX, then export). No black box: you control every prompt, asset, model, and setting.

12 days ago

Slovakia Payments Mcp

@junter1989k-ai

12 days ago