Command Palette

Search for a command to run...

UnylyUnyly
Весь каталог

Cognition Wheel

БесплатноНе проверен

Enables querying multiple AI models in parallel (Claude, Gemini, O3) and synthesizing their responses using anonymous analysis to reduce bias, providing a compr

GitHubEmbed

Описание

Enables querying multiple AI models in parallel (Claude, Gemini, O3) and synthesizing their responses using anonymous analysis to reduce bias, providing a comprehensive answer.

README

A Model Context Protocol (MCP) server that implements a "wisdom of crowds" approach to AI reasoning by consulting multiple state-of-the-art language models in parallel and synthesizing their responses.

Quick Start

Option 1: Use with npx (Recommended)

# Run directly with npx (no installation needed)
npx mcp-cognition-wheel

# Or install globally
npm install -g mcp-cognition-wheel
mcp-cognition-wheel

Option 2: Build from source

  1. Clone the repository
  2. Install dependencies: pnpm install
  3. Copy .env.example to .env and add your API keys
  4. Build the project: pnpm run build

How It Works

The Cognition Wheel follows a three-phase process:

  1. Parallel Consultation: Simultaneously queries three different AI models:

    • Claude-4-Opus (Anthropic)
    • Gemini-2.5-Pro (Google)
    • O3 (OpenAI)
  2. Anonymous Analysis: Uses code names (Alpha, Beta, Gamma) to eliminate bias during the synthesis phase

  3. Smart Synthesis: Randomly selects one of the models to act as a synthesizer, which analyzes all responses and produces a final, comprehensive answer

Features

  • Parallel Processing: All models are queried simultaneously for faster results
  • Bias Reduction: Anonymous code names prevent synthesizer bias toward specific models
  • Internet Search: Optional web search capabilities for all models
  • Detailed Logging: Comprehensive debug logs for transparency and troubleshooting
  • Robust Error Handling: Graceful degradation when individual models fail

Installation

Option 1: Use with npx (Recommended)

# Run directly with npx (no installation needed)
npx mcp-cognition-wheel

# Or install globally
npm install -g mcp-cognition-wheel
mcp-cognition-wheel

Option 2: Build from source

  1. Clone the repository
  2. Install dependencies: pnpm install
  3. Copy .env.example to .env and add your API keys
  4. Build the project: pnpm run build

Usage

This is an MCP server designed to be used with MCP-compatible clients like Claude Desktop or other MCP tools.

Required Environment Variables

  • ANTHROPIC_API_KEY: Your Anthropic API key
  • GOOGLE_GENERATIVE_AI_API_KEY: Your Google AI API key
  • OPENAI_API_KEY: Your OpenAI API key

Using with Cursor

Based on the guide from this dev.to article, here's how to integrate with Cursor:

Option 1: Using npx (Recommended)

  1. Open Cursor Settings:

    • Go to Settings → MCP
    • Click "Add new MCP server"
  2. Configure the server:

    • Name: cognition-wheel
    • Command: npx
    • Args: ["-y", "mcp-cognition-wheel"]

    Example configuration:

    {
      "cognition-wheel": {
        "command": "npx",
        "args": ["-y", "mcp-cognition-wheel"],
        "env": {
          "ANTHROPIC_API_KEY": "your_anthropic_key",
          "GOOGLE_GENERATIVE_AI_API_KEY": "your_google_key", 
          "OPENAI_API_KEY": "your_openai_key"
        }
      }
    }
    

Option 2: Using local build

  1. Build the project (if not already done):

    pnpm run build
    
  2. Configure the server:

    • Name: cognition-wheel
    • Command: node
    • Args: ["/absolute/path/to/your/cognition-wheel/dist/app.js"]

    Example configuration:

    {
      "cognition-wheel": {
        "command": "node",
        "args": [
          "/Users/yourname/path/to/cognition-wheel/dist/app.js"
        ],
        "env": {
          "ANTHROPIC_API_KEY": "your_anthropic_key",
          "GOOGLE_GENERATIVE_AI_API_KEY": "your_google_key", 
          "OPENAI_API_KEY": "your_openai_key"
        }
      }
    }
    
  3. Test the integration:

    • Enter Agent mode in Cursor
    • Ask a complex question that would benefit from multiple AI perspectives
    • The cognition_wheel tool should be automatically triggered

Tool Usage

The server provides a single tool called cognition_wheel with the following parameters:

  • context: Background information and context for the problem
  • question: The specific question you want answered
  • enable_internet_search: Boolean flag to enable web search capabilities

Development

  • pnpm run dev: Watch mode for development
  • pnpm run build: Build the TypeScript code
  • pnpm run start: Run the server directly with tsx

Docker

Build and run with Docker:

# Build the image
docker build -t cognition-wheel .

# Run with environment variables
docker run --rm \
  -e ANTHROPIC_API_KEY=your_key \
  -e GOOGLE_GENERATIVE_AI_API_KEY=your_key \
  -e OPENAI_API_KEY=your_key \
  cognition-wheel

License

MIT

from github.com/Hormold/cognition-wheel

Установка Cognition Wheel

У этого сервера нет опубликованного пакета — он собирается из исходников. Открой репозиторий и следуй инструкции в README.

▸ github.com/Hormold/cognition-wheel

FAQ

Cognition Wheel MCP бесплатный?

Да, Cognition Wheel MCP бесплатный — установка в пару кликов через Unyly без оплаты.

Нужен ли API-ключ для Cognition Wheel?

Нет, Cognition Wheel работает без API-ключей и переменных окружения.

Cognition Wheel — hosted или self-hosted?

Доступен hosted-вариант: Unyly запускает сервер в облаке, локальная установка не обязательна.

Как установить Cognition Wheel в Claude Desktop, Claude Code или Cursor?

Открой Cognition Wheel на unyly.org, выбери вкладку своего клиента (Claude Desktop, Claude Code, Cursor) и нажми Install — конфиг сгенерируется автоматически, без правки JSON.

Похожие MCP

Compare Cognition Wheel with

Не уверен что выбрать?

Найди свой стек за 60 секунд

Автор?

Embed-бейдж для README

Похожее

Все в категории ai