Skip to main content
Glama

mcp-rubber-duck

by nesquikm
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Remote
MIT License
223
81

šŸ¦† 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!

npm version Docker Image MCP Registry

Table of Contents

Related MCP server: Zen MCP Server

Features

  • šŸ”Œ Universal OpenAI Compatibility: Works with any OpenAI-compatible API endpoint

  • šŸ¦† Multiple Ducks: Configure and query multiple LLM providers simultaneously

  • šŸ’¬ Conversation Management: Maintain context across multiple messages

  • šŸ›ļø Duck Council: Get responses from all your configured LLMs at once

  • šŸ—³ļø Consensus Voting: Multi-duck voting with reasoning and confidence scores

  • āš–ļø LLM-as-Judge: Have ducks evaluate and rank each other's responses

  • šŸ”„ Iterative Refinement: Two ducks collaboratively improve responses

  • šŸŽ“ Structured Debates: Oxford, Socratic, and adversarial debate formats

  • šŸ’¾ Response Caching: Avoid duplicate API calls with intelligent caching

  • šŸ” Automatic Failover: Falls back to other providers if primary fails

  • šŸ“Š Health Monitoring: Real-time health checks for all providers

  • šŸ”— MCP Bridge: Connect ducks to other MCP servers for extended functionality

  • šŸ›”ļø Granular Security: Per-server approval controls with session-based approvals

  • šŸŽØ Fun Duck Theme: Rubber duck debugging with personality!

Supported Providers

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

  • OpenAI (GPT-5.1, o3, o4-mini)

  • Google Gemini (Gemini 3, Gemini 2.5 Pro/Flash)

  • Anthropic (via OpenAI-compatible endpoints)

  • Groq (Llama 4, Llama 3.3)

  • Together AI (Llama 4, Qwen, 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

# Install globally npm install -g mcp-rubber-duck # Or use npx directly in Claude Desktop config npx mcp-rubber-duck

Using Claude Desktop? Jump to Claude Desktop Configuration.

Installation

Prerequisites

  • Node.js 20 or higher

  • npm or yarn

  • At least one API key for a supported provider

Installation Methods

Option 1: Install from NPM

npm install -g mcp-rubber-duck

Option 2: Install from Source

# Clone the repository git clone https://github.com/nesquikm/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-5.1 # Optional: defaults to gpt-5.1 # 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 Providers (you can add multiple) # Format: CUSTOM_{NAME}_* where NAME becomes the provider key (lowercase) # Example: Add provider "myapi" CUSTOM_MYAPI_API_KEY=... CUSTOM_MYAPI_BASE_URL=https://api.example.com/v1 CUSTOM_MYAPI_DEFAULT_MODEL=custom-model # Optional CUSTOM_MYAPI_MODELS=model1,model2 # Optional: comma-separated list CUSTOM_MYAPI_NICKNAME=My Custom Duck # Optional: display name # Example: Add provider "azure" CUSTOM_AZURE_API_KEY=... CUSTOM_AZURE_BASE_URL=https://mycompany.openai.azure.com/v1 # Global Settings DEFAULT_PROVIDER=openai DEFAULT_TEMPERATURE=0.7 LOG_LEVEL=info # MCP Bridge Settings (Optional) MCP_BRIDGE_ENABLED=true # Enable ducks to access external MCP servers MCP_APPROVAL_MODE=trusted # always, trusted, or never MCP_APPROVAL_TIMEOUT=300 # seconds # MCP Server: Context7 Documentation (Example) MCP_SERVER_CONTEXT7_TYPE=http MCP_SERVER_CONTEXT7_URL=https://mcp.context7.com/mcp MCP_SERVER_CONTEXT7_ENABLED=true # Per-server trusted tools MCP_TRUSTED_TOOLS_CONTEXT7=* # Trust all Context7 tools # 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: Install

Choose one of these options:

Option A: NPM (Recommended)

npm install -g mcp-rubber-duck

Option B: From Source (see Installation from Source)

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:

If installed via NPM:

{ "mcpServers": { "rubber-duck": { "command": "mcp-rubber-duck", "env": { "MCP_SERVER": "true", "OPENAI_API_KEY": "your-openai-api-key-here", "GEMINI_API_KEY": "your-gemini-api-key-here", "DEFAULT_PROVIDER": "openai" } } } }

If installed from source:

{ "mcpServers": { "rubber-duck": { "command": "node", "args": ["/absolute/path/to/mcp-rubber-duck/dist/index.js"], "env": { "MCP_SERVER": "true", "OPENAI_API_KEY": "your-openai-api-key-here", "GEMINI_API_KEY": "your-gemini-api-key-here", "DEFAULT_PROVIDER": "openai" } } } }

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

  • your-openai-api-key-here ā†’ Your OpenAI API key (starts with sk-)

  • your-gemini-api-key-here ā†’ Your Gemini API key from Google AI Studio

Note: MCP_SERVER: "true" is required - this tells rubber-duck to run as an MCP server for any MCP client (not related to the MCP Bridge feature).

Tip: See Configuration for additional options like LOG_LEVEL, custom model defaults, and duck nicknames.

Step 3: Restart Claude Desktop

  1. Completely quit Claude Desktop (āŒ˜+Q on Mac)

  2. Launch Claude Desktop again

  3. 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:

  • āœ… GPT Duck (openai) - Healthy

  • āœ… 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

  1. Check API Keys: Ensure your API keys are correctly entered without typos

  2. Verify Build: Run ls -la dist/index.js to confirm the project built successfully

  3. Check Logs: Look for errors in Claude Desktop's developer console

  4. Restart: Fully quit and restart Claude Desktop after config changes

Connection Issues

  1. Config File Path: Double-check you're editing the correct config file path

  2. JSON Syntax: Validate your JSON syntax (no trailing commas, proper quotes)

  3. Absolute Paths: Ensure you're using the full absolute path to dist/index.js

  4. File Permissions: Verify Claude Desktop can read the dist directory

Health Check Failures

If ducks show as unhealthy:

  1. API Keys: Verify keys are valid and have sufficient credits/quota

  2. Network: Check internet connection and firewall settings

  3. Rate Limits: Some providers have strict rate limits for new accounts

MCP Bridge - Connect to Other MCP Servers

The MCP Bridge allows your ducks to access tools from other MCP servers, extending their capabilities beyond just chat. Your ducks can now search documentation, access files, query APIs, and much more!

Note: This is different from the MCP server integration above:

  • MCP Bridge (MCP_BRIDGE_ENABLED): Ducks USE external MCP servers as clients

  • MCP Server (MCP_SERVER): Rubber-duck SERVES as an MCP server to any MCP client

Quick Setup

Add these environment variables to enable MCP Bridge:

# Basic MCP Bridge Configuration MCP_BRIDGE_ENABLED="true" # Enable ducks to access external MCP servers MCP_APPROVAL_MODE="trusted" # always, trusted, or never MCP_APPROVAL_TIMEOUT="300" # 5 minutes # Example: Context7 Documentation Server MCP_SERVER_CONTEXT7_TYPE="http" MCP_SERVER_CONTEXT7_URL="https://mcp.context7.com/mcp" MCP_SERVER_CONTEXT7_ENABLED="true" # Trust all Context7 tools (no approval needed) MCP_TRUSTED_TOOLS_CONTEXT7="*"

Approval Modes

always: Every tool call requires approval (with session-based memory)

  • First use of a tool ā†’ requires approval

  • Subsequent uses of the same tool ā†’ automatic (until restart)

trusted: Only untrusted tools require approval

  • Tools in trusted lists execute immediately

  • Unknown tools require approval

never: All tools execute immediately (use with caution)

Per-Server Trusted Tools

Configure trust levels per MCP server for granular security:

# Trust all tools from Context7 (documentation server) MCP_TRUSTED_TOOLS_CONTEXT7="*" # Trust specific filesystem operations only MCP_TRUSTED_TOOLS_FILESYSTEM="read-file,list-directory" # Trust specific GitHub tools MCP_TRUSTED_TOOLS_GITHUB="get-repo-info,list-issues" # Global fallback for servers without specific config MCP_TRUSTED_TOOLS="common-safe-tool"

MCP Server Configuration

Configure MCP servers using environment variables:

HTTP Servers

MCP_SERVER_{NAME}_TYPE="http" MCP_SERVER_{NAME}_URL="https://api.example.com/mcp" MCP_SERVER_{NAME}_API_KEY="your-api-key" # Optional MCP_SERVER_{NAME}_ENABLED="true"

STDIO Servers

MCP_SERVER_{NAME}_TYPE="stdio" MCP_SERVER_{NAME}_COMMAND="python" MCP_SERVER_{NAME}_ARGS="/path/to/script.py,--arg1,--arg2" MCP_SERVER_{NAME}_ENABLED="true"

Example: Enable Context7 Documentation

# Enable MCP Bridge MCP_BRIDGE_ENABLED="true" MCP_APPROVAL_MODE="trusted" # Configure Context7 server MCP_SERVER_CONTEXT7_TYPE="http" MCP_SERVER_CONTEXT7_URL="https://mcp.context7.com/mcp" MCP_SERVER_CONTEXT7_ENABLED="true" # Trust all Context7 tools MCP_TRUSTED_TOOLS_CONTEXT7="*"

Now your ducks can search and retrieve documentation from Context7:

Ask: "Can you find React hooks documentation from Context7 and return only the key concepts?" Duck: *searches Context7 and returns focused, essential React hooks information*

Token Optimization Benefits

Smart Token Management: Ducks can retrieve comprehensive data from MCP servers but return only the essential information you need, saving tokens in your host LLM conversations:

  • Ask for specifics: "Find TypeScript interfaces documentation and return only the core concepts"

  • Duck processes full docs: Accesses complete documentation from Context7

  • Returns condensed results: Provides focused, relevant information while filtering out unnecessary details

  • Token savings: Reduces response size by 70-90% compared to raw documentation dumps

Example Workflow:

You: "Find Express.js routing concepts from Context7, keep it concise" Duck: *Retrieves full Express docs, processes, and returns only routing essentials* Result: 500 tokens instead of 5,000+ tokens of raw documentation

Session-Based Approvals

When using always mode, the system remembers your approvals:

  1. First time: "Duck wants to use search-docs - Approve? āœ…"

  2. Next time: Duck uses search-docs automatically (no new approval needed)

  3. Different tool: "Duck wants to use get-examples - Approve? āœ…"

  4. Restart: Session memory clears, start over

This eliminates approval fatigue while maintaining security!

Available Tools

Basic Tools

šŸ¦† ask_duck

Ask a single question to a specific LLM provider. When MCP Bridge is enabled, ducks can automatically access tools from connected MCP servers.

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

šŸ’¬ 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 }

šŸ§¹ clear_conversations

Clear all conversation history and start fresh. Useful when switching topics or when context becomes too large.

{ // No parameters required }

šŸ“‹ list_ducks

List all configured providers and their health status.

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

šŸ“Š 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 }

šŸ” 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 }

šŸ›ļø duck_council

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

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

Multi-Agent Consensus & Debate Tools

Research-backed tools for multi-agent coordination.

šŸ—³ļø duck_vote

Have multiple ducks vote on options with reasoning and confidence scores.

{ "question": "Best approach for error handling?", "options": ["try-catch", "Result type", "Either monad"], "voters": ["openai", "gemini"], // Optional, uses all if not specified "require_reasoning": true // Optional, default: true }

Returns vote tally, confidence scores, and consensus level (unanimous, majority, plurality, split, none).

āš–ļø duck_judge

Have one duck evaluate and rank other ducks' responses. Use after duck_council.

{ "responses": [/* responses from duck_council */], "judge": "openai", // Optional, uses first available "criteria": ["accuracy", "completeness", "clarity"], // Optional "persona": "senior engineer" // Optional, e.g., "security expert" }

šŸ”„ duck_iterate

Iteratively refine a response between two ducks.

{ "prompt": "Write a function to validate email addresses", "providers": ["openai", "gemini"], // Exactly 2 providers "mode": "critique-improve", // or "refine" "iterations": 3 // Optional, default: 3, max: 10 }

Modes:

  • refine: Each duck improves the previous response

  • critique-improve: Alternates between critiquing and improving

šŸŽ“ duck_debate

Structured multi-round debate between ducks.

{ "prompt": "Should startups use microservices or monolith for MVP?", "format": "oxford", // "oxford", "socratic", or "adversarial" "rounds": 2, // Optional, default: 3 "providers": ["openai", "gemini"], // Optional, uses all if not specified "synthesizer": "openai" // Optional, duck to synthesize debate }

Formats:

  • oxford: Structured pro/con arguments

  • socratic: Question-based philosophical exploration

  • adversarial: One defends, others attack weaknesses

MCP Bridge Tools

Tools for managing MCP server connections and tool approvals.

šŸ”— mcp_status

Get status of MCP Bridge, connected servers, and pending approvals.

{ // No parameters required }

āœ… get_pending_approvals

Get list of pending MCP tool approvals from ducks.

{ "duck": "openai" // Optional, filter by duck name }

šŸ›”ļø approve_mcp_request

Approve or deny a duck's MCP tool request.

{ "approval_id": "abc123", // Required "decision": "approve", // "approve" or "deny" "reason": "Not needed" // Optional, reason for denial }

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?" });

Multi-Agent Voting

// Have ducks vote on a decision await duck_vote({ question: "Best database for a real-time chat app?", options: ["PostgreSQL", "MongoDB", "Redis", "Cassandra"] }); // Returns: Winner with consensus level (unanimous/majority/split)

Judge Responses

// First, get responses from council const responses = await duck_council({ prompt: "Implement a rate limiter" }); // Then have a duck judge them await duck_judge({ responses: responses, criteria: ["correctness", "efficiency", "readability"], persona: "senior backend engineer" });

Iterative Refinement

// Two ducks collaborate to improve a solution await duck_iterate({ prompt: "Write a TypeScript function to deep clone objects", providers: ["openai", "gemini"], mode: "critique-improve", iterations: 3 });

Structured Debate

// Oxford-style debate on architecture await duck_debate({ prompt: "Monorepo vs polyrepo for a growing startup", format: "oxford", rounds: 3 });

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)

  1. Download LM Studio from https://lmstudio.ai/

  2. Load a model in LM Studio

  3. Start the local server (provides OpenAI-compatible endpoint at localhost:1234/v1)

Google Gemini

  1. Get API key from Google AI Studio

  2. Add to environment: GEMINI_API_KEY=...

  3. Uses OpenAI-compatible endpoint (beta)

Groq

  1. Get API key from https://console.groq.com/keys

  2. Add to environment: GROQ_API_KEY=gsk_...

Together AI

  1. Get API key from https://api.together.xyz/

  2. Add to environment: TOGETHER_API_KEY=...

Verifying OpenAI Compatibility

To check if a provider is OpenAI-compatible:

  1. Look for /v1/chat/completions endpoint in their API docs

  2. Check if they support the OpenAI SDK

  3. 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

MCP Rubber Duck provides multi-platform Docker support, working on macOS (Intel & Apple Silicon), Linux (x86_64 & ARM64), Windows (WSL2), and Raspberry Pi 3+.

Quick Start with Pre-built Image

The easiest way to get started is with our pre-built multi-architecture image:

# Pull the image (works on all platforms) docker pull ghcr.io/nesquikm/mcp-rubber-duck:latest # Create environment file cp .env.template .env # Edit .env and add your API keys # Run with Docker Compose (recommended) docker compose up -d

Platform-Specific Deployment

Desktop/Server (macOS, Linux, Windows)

# Use desktop-optimized settings ./scripts/deploy.sh --platform desktop # Or with more resources and local AI ./scripts/deploy.sh --platform desktop --profile with-ollama

Raspberry Pi

# Use Pi-optimized settings (memory limits, etc.) ./scripts/deploy.sh --platform pi # Or copy optimized config directly cp .env.pi.example .env # Edit .env and add your API keys docker compose up -d

Remote Deployment via SSH

# Deploy to remote Raspberry Pi ./scripts/deploy.sh --mode ssh --ssh-host pi@192.168.1.100

Universal Deployment Script

The scripts/deploy.sh script auto-detects your platform and applies optimal settings:

# Auto-detect platform and deploy ./scripts/deploy.sh # Options: ./scripts/deploy.sh --help

Available options:

  • --mode: docker (default), local, or ssh

  • --platform: pi, desktop, or auto (default)

  • --profile: lightweight, desktop, with-ollama

  • --ssh-host: For remote deployment

Platform-Specific Configuration

Raspberry Pi (Memory-Optimized)

# .env.pi.example - Optimized for Pi 3+ DOCKER_CPU_LIMIT=1.5 DOCKER_MEMORY_LIMIT=512M NODE_OPTIONS=--max-old-space-size=256

Desktop/Server (High-Performance)

# .env.desktop.example - Optimized for powerful systems DOCKER_CPU_LIMIT=4.0 DOCKER_MEMORY_LIMIT=2G NODE_OPTIONS=--max-old-space-size=1024

Docker Compose Profiles

# Default profile (lightweight, good for Pi) docker compose up -d # Desktop profile (higher resource limits) docker compose --profile desktop up -d # With local Ollama AI docker compose --profile with-ollama up -d

Build Multi-Architecture Images

For developers who want to build and publish their own multi-architecture images:

# Build for AMD64 + ARM64 ./scripts/build-multiarch.sh --platforms linux/amd64,linux/arm64 # Build and push to GitHub Container Registry ./scripts/gh-deploy.sh --public

Claude Desktop with Remote Docker

Connect Claude Desktop to MCP Rubber Duck running on a remote system:

{ "mcpServers": { "rubber-duck-remote": { "command": "ssh", "args": [ "user@remote-host", "docker exec -i mcp-rubber-duck node /app/dist/index.js" ] } } }

Platform Compatibility

Platform

Architecture

Status

Notes

macOS Intel

AMD64

āœ… Full

Via Docker Desktop

macOS Apple Silicon

ARM64

āœ… Full

Native ARM64 support

Linux x86_64

AMD64

āœ… Full

Direct Docker support

Linux ARM64

ARM64

āœ… Full

Servers, Pi 4+

Raspberry Pi 3+

ARM64

āœ… Optimized

Memory-limited config

Windows

AMD64

āœ… Full

Via Docker Desktop + WSL2

Manual Docker Commands

If you prefer not to use docker-compose:

# Raspberry Pi docker run -d \ --name mcp-rubber-duck \ --memory=512m --cpus=1.5 \ --env-file .env \ --restart unless-stopped \ ghcr.io/nesquikm/mcp-rubber-duck:latest # Desktop/Server docker run -d \ --name mcp-rubber-duck \ --memory=2g --cpus=4 \ --env-file .env \ --restart unless-stopped \ ghcr.io/nesquikm/mcp-rubber-duck:latest

Architecture

mcp-rubber-duck/ ā”œā”€ā”€ src/ ā”‚ ā”œā”€ā”€ server.ts # MCP server implementation ā”‚ ā”œā”€ā”€ config/ # Configuration management ā”‚ ā”œā”€ā”€ providers/ # OpenAI client wrapper ā”‚ ā”œā”€ā”€ tools/ # MCP tool implementations ā”‚ ā”œā”€ā”€ services/ # Health, cache, conversations ā”‚ ā””ā”€ā”€ utils/ # Logging, ASCII art ā”œā”€ā”€ config/ # Configuration examples ā””ā”€ā”€ tests/ # Test suites

Troubleshooting

Provider Not Working

  1. Check API key is correctly set

  2. Verify endpoint URL is correct

  3. Run health check: list_ducks({ check_health: true })

  4. 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

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

šŸ¦† Want to help make our duck pond better?

We love contributions! Whether you're fixing bugs, adding features, or teaching our ducks new tricks, we'd love to have you join the flock.

Check out our Contributing Guide to get started. We promise it's more fun than a regular contributing guide - it has ducks! šŸ¦†

Quick start for contributors:

  1. Fork the repository

  2. Create a feature branch

  3. Follow our conventional commit guidelines

  4. Add tests for new functionality

  5. 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

Changelog

See CHANGELOG.md for a detailed history of changes and releases.

Registry & Directory

MCP Rubber Duck is available through multiple channels:

Support

šŸ¦† Happy Debugging with your AI Duck Panel! šŸ¦†

This server cannot be installed

-
security - not tested
A
license - permissive license
-
quality - not tested

How are these scores calculated?

Resources

New MCP Servers

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/nesquikm/mcp-rubber-duck'

If you have feedback or need assistance with the MCP directory API, please join our Discord server