🦆 MCP Rubber Duck

An MCP (Model Context Protocol) server that acts as a bridge to query multiple OpenAI-compatible LLMs. Just like rubber duck debugging, explain your problems to various AI "ducks" and get different perspectives!

     __
   <(o )___
    ( ._> /
     `---'  Quack! Ready to debug!

Features

🔌 Universal OpenAI Compatibility: Works with any OpenAI-compatible API endpoint
🦆 Multiple Ducks: Configure and query multiple LLM providers simultaneously
💬 Conversation Management: Maintain context across multiple messages
🏛️ Duck Council: Get responses from all your configured LLMs at once
💾 Response Caching: Avoid duplicate API calls with intelligent caching
🔄 Automatic Failover: Falls back to other providers if primary fails
📊 Health Monitoring: Real-time health checks for all providers
🎨 Fun Duck Theme: Rubber duck debugging with personality!

Supported Providers

Any provider with an OpenAI-compatible API endpoint, including:

OpenAI (GPT-4, GPT-3.5)
Google Gemini (Gemini 2.5 Flash, Gemini 2.0 Flash)
Anthropic (via OpenAI-compatible endpoints)
Groq (Llama, Mixtral, Gemma)
Together AI (Llama, Mixtral, and more)
Perplexity (Online models with web search)
Anyscale (Open source models)
Azure OpenAI (Microsoft-hosted OpenAI)
Ollama (Local models)
LM Studio (Local models)
Custom (Any OpenAI-compatible endpoint)

Quick Start

For Claude Desktop Users

👉 Complete Claude Desktop setup instructions below in Claude Desktop Configuration

Installation

Prerequisites

Node.js 20 or higher
npm or yarn
At least one API key for a supported provider

Install from Source

# Clone the repository
git clone https://github.com/yourusername/mcp-rubber-duck.git
cd mcp-rubber-duck

# Install dependencies
npm install

# Build the project
npm run build

# Run the server
npm start

Configuration

Method 1: Environment Variables

Create a .env file in the project root:

# OpenAI
OPENAI_API_KEY=sk-...
OPENAI_DEFAULT_MODEL=gpt-4o-mini  # Optional: defaults to gpt-4o-mini

# Google Gemini
GEMINI_API_KEY=...
GEMINI_DEFAULT_MODEL=gemini-2.5-flash  # Optional: defaults to gemini-2.5-flash

# Groq
GROQ_API_KEY=gsk_...
GROQ_DEFAULT_MODEL=llama-3.3-70b-versatile  # Optional: defaults to llama-3.3-70b-versatile

# Ollama (Local)
OLLAMA_BASE_URL=http://localhost:11434/v1  # Optional
OLLAMA_DEFAULT_MODEL=llama3.2  # Optional: defaults to llama3.2

# Together AI
TOGETHER_API_KEY=...

# Custom Provider
CUSTOM_API_KEY=...
CUSTOM_BASE_URL=https://api.example.com/v1
CUSTOM_DEFAULT_MODEL=custom-model  # Optional: defaults to custom-model

# Global Settings
DEFAULT_PROVIDER=openai
DEFAULT_TEMPERATURE=0.7
LOG_LEVEL=info

# Optional: Custom Duck Nicknames (Have fun with these!)
OPENAI_NICKNAME="DUCK-4"              # Optional: defaults to "GPT Duck"
GEMINI_NICKNAME="Duckmini"            # Optional: defaults to "Gemini Duck"
GROQ_NICKNAME="Quackers"              # Optional: defaults to "Groq Duck"
OLLAMA_NICKNAME="Local Quacker"       # Optional: defaults to "Local Duck"
CUSTOM_NICKNAME="My Special Duck"     # Optional: defaults to "Custom Duck"

Note: Duck nicknames are completely optional! If you don't set them, you'll get the charming defaults (GPT Duck, Gemini Duck, etc.). If you use a config.json file, those nicknames take priority over environment variables.

Method 2: Configuration File

Create a config/config.json file based on the example:

cp config/config.example.json config/config.json
# Edit config/config.json with your API keys and preferences

Claude Desktop Configuration

This is the most common setup method for using MCP Rubber Duck with Claude Desktop.

Step 1: Build the Project

First, ensure the project is built:

# Clone the repository
git clone https://github.com/yourusername/mcp-rubber-duck.git
cd mcp-rubber-duck

# Install dependencies and build
npm install
npm run build

Step 2: Configure Claude Desktop

Edit your Claude Desktop config file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json

Add the MCP server configuration:

{
  "mcpServers": {
    "rubber-duck": {
      "command": "node",
      "args": ["/absolute/path/to/mcp-rubber-duck/dist/index.js"],
      "env": {
        "OPENAI_API_KEY": "your-openai-api-key-here",
        "OPENAI_DEFAULT_MODEL": "gpt-4o-mini",
        "GEMINI_API_KEY": "your-gemini-api-key-here", 
        "GEMINI_DEFAULT_MODEL": "gemini-2.5-flash",
        "DEFAULT_PROVIDER": "openai",
        "LOG_LEVEL": "info"
      }
    }
  }
}

Important: Replace the placeholder API keys with your actual keys:

your-openai-api-key-here → Your OpenAI API key (starts with sk-)
your-gemini-api-key-here → Your Gemini API key from Google AI Studio

Step 3: Restart Claude Desktop

Completely quit Claude Desktop (⌘+Q on Mac)
Launch Claude Desktop again
The MCP server should connect automatically

Step 4: Test the Integration

Once restarted, test these commands in Claude:

Check Duck Health

Use the list_ducks tool with check_health: true

Should show:

✅ GPT Duck (openai) - Healthy
✅ Gemini Duck (gemini) - Healthy

List Available Models

Use the list_models tool

Ask a Specific Duck

Use the ask_duck tool with prompt: "What is rubber duck debugging?", provider: "openai"

Compare Multiple Ducks

Use the compare_ducks tool with prompt: "Explain async/await in JavaScript"

Test Specific Models

Use the ask_duck tool with prompt: "Hello", provider: "openai", model: "gpt-4"

Troubleshooting Claude Desktop Setup

If Tools Don't Appear

Check API Keys: Ensure your API keys are correctly entered without typos
Verify Build: Run ls -la dist/index.js to confirm the project built successfully
Check Logs: Look for errors in Claude Desktop's developer console
Restart: Fully quit and restart Claude Desktop after config changes

Connection Issues

Config File Path: Double-check you're editing the correct config file path
JSON Syntax: Validate your JSON syntax (no trailing commas, proper quotes)
Absolute Paths: Ensure you're using the full absolute path to dist/index.js
File Permissions: Verify Claude Desktop can read the dist directory

Health Check Failures

If ducks show as unhealthy:

API Keys: Verify keys are valid and have sufficient credits/quota
Network: Check internet connection and firewall settings
Rate Limits: Some providers have strict rate limits for new accounts

Available Tools

🦆 ask_duck

Ask a single question to a specific LLM provider.

{
  "prompt": "What is rubber duck debugging?",
  "provider": "openai",  // Optional, uses default if not specified
  "temperature": 0.7     // Optional
}

💬 chat_with_duck

Have a conversation with context maintained across messages.

{
  "conversation_id": "debug-session-1",
  "message": "Can you help me debug this code?",
  "provider": "groq"  // Optional, can switch providers mid-conversation
}

📋 list_ducks

List all configured providers and their health status.

{
  "check_health": true  // Optional, performs fresh health check
}

📊 list_models

List available models for LLM providers.

{
  "provider": "openai",     // Optional, lists all if not specified
  "fetch_latest": false     // Optional, fetch latest from API vs cached
}

🔍 compare_ducks

Ask the same question to multiple providers simultaneously.

{
  "prompt": "What's the best programming language?",
  "providers": ["openai", "groq", "ollama"]  // Optional, uses all if not specified
}

🏛️ duck_council

Get responses from all configured ducks - like a panel discussion!

{
  "prompt": "How should I architect a microservices application?"
}

Usage Examples

Basic Query

// Ask the default duck
await ask_duck({ 
  prompt: "Explain async/await in JavaScript" 
});

Conversation

// Start a conversation
await chat_with_duck({
  conversation_id: "learning-session",
  message: "What is TypeScript?"
});

// Continue the conversation
await chat_with_duck({
  conversation_id: "learning-session", 
  message: "How does it differ from JavaScript?"
});

Compare Responses

// Get different perspectives
await compare_ducks({
  prompt: "What's the best way to handle errors in Node.js?",
  providers: ["openai", "groq", "ollama"]
});

Duck Council

// Convene the council for important decisions
await duck_council({
  prompt: "Should I use REST or GraphQL for my API?"
});

Provider-Specific Setup

Ollama (Local)

# Install Ollama
curl -fsSL https://ollama.ai/install.sh | sh

# Pull a model
ollama pull llama3.2

# Ollama automatically provides OpenAI-compatible endpoint at localhost:11434/v1

LM Studio (Local)

Download LM Studio from https://lmstudio.ai/
Load a model in LM Studio
Start the local server (provides OpenAI-compatible endpoint at localhost:1234/v1)

Google Gemini

Get API key from Google AI Studio
Add to environment: GEMINI_API_KEY=...
Uses OpenAI-compatible endpoint (beta)

Groq

Get API key from https://console.groq.com/keys
Add to environment: GROQ_API_KEY=gsk_...

Together AI

Get API key from https://api.together.xyz/
Add to environment: TOGETHER_API_KEY=...

Verifying OpenAI Compatibility

To check if a provider is OpenAI-compatible:

Look for /v1/chat/completions endpoint in their API docs
Check if they support the OpenAI SDK
Test with curl:

curl -X POST "https://api.provider.com/v1/chat/completions" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "model-name",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Development

Run in Development Mode

npm run dev

Run Tests

npm test

Lint Code

npm run lint

Type Checking

npm run typecheck

Docker Support

Build Docker Image

docker build -t mcp-rubber-duck .

Run with Docker

docker run -it \
  -e OPENAI_API_KEY=sk-... \
  -e GROQ_API_KEY=gsk_... \
  mcp-rubber-duck

Architecture

mcp-rubber-duck/
├── src/
│   ├── server.ts           # MCP server implementation
│   ├── config/             # Configuration management
│   ├── providers/          # OpenAI client wrapper
│   ├── tools/              # MCP tool implementations
│   ├── services/           # Health, cache, conversations
│   └── utils/              # Logging, ASCII art
├── config/                 # Configuration examples
└── tests/                  # Test suites

Troubleshooting

Provider Not Working

Check API key is correctly set
Verify endpoint URL is correct
Run health check: list_ducks({ check_health: true })
Check logs for detailed error messages

Connection Issues

For local providers (Ollama, LM Studio), ensure they're running
Check firewall settings for local endpoints
Verify network connectivity to cloud providers

Rate Limiting

Enable caching to reduce API calls
Configure failover to alternate providers
Adjust max_retries and timeout settings

Contributing

Contributions are welcome! Please:

Fork the repository
Create a feature branch
Add tests for new functionality
Submit a pull request

License

MIT License - see LICENSE file for details

Acknowledgments

Inspired by the rubber duck debugging method
Built on the Model Context Protocol (MCP)
Uses OpenAI SDK for universal compatibility

Support

Report issues: https://github.com/yourusername/mcp-rubber-duck/issues
Documentation: https://github.com/yourusername/mcp-rubber-duck/wiki
Discussions: https://github.com/yourusername/mcp-rubber-duck/discussions

🦆 Happy Debugging with your AI Duck Panel! 🦆

Rubber Duck

🦆 MCP Rubber Duck

Features

Supported Providers

Quick Start

For Claude Desktop Users

Installation

Prerequisites

Install from Source

Configuration

Method 1: Environment Variables

Method 2: Configuration File

Claude Desktop Configuration

Step 1: Build the Project

Step 2: Configure Claude Desktop

Step 3: Restart Claude Desktop

Step 4: Test the Integration

Check Duck Health

List Available Models

Ask a Specific Duck

Compare Multiple Ducks

Test Specific Models

Troubleshooting Claude Desktop Setup

If Tools Don't Appear

Connection Issues

Health Check Failures

Available Tools

🦆 ask_duck

💬 chat_with_duck

📋 list_ducks

📊 list_models

🔍 compare_ducks

🏛️ duck_council

Usage Examples

Basic Query

Conversation

Compare Responses

Duck Council

Provider-Specific Setup

Ollama (Local)

LM Studio (Local)

Google Gemini

Groq

Together AI

Verifying OpenAI Compatibility

Development

Run in Development Mode

Run Tests

Lint Code

Type Checking

Docker Support

Build Docker Image

Run with Docker

Architecture

Troubleshooting

Provider Not Working

Connection Issues

Rate Limiting

Contributing

License

Acknowledgments

Support

Be the First to Experience MCP Now