Rubber Duck
An MCP server that acts as a bridge to query multiple OpenAI-compatible LLMs with MCP tool access. Just like rubber duck debugging, explain your problems to various AI 'ducks' who can actually research and get different perspectives!
What is Rubber Duck?
Rubber Duck is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp server that acts as a bridge to query multiple openai-compatible llms with mcp tool access. just like rubber duck debugging, explain your problems to various ai 'ducks' who can actually research a...
An MCP server that acts as a bridge to query multiple OpenAI-compatible LLMs with MCP tool access. Just like rubber duck debugging, explain your problems to various AI 'ducks' who can actually research and get different perspectives!
This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- ask_duck
- chat_with_duck
- clear_conversations
- list_ducks
- list_models
Use Cases
Maintainer
Works with
Installation
NPM
npx -y mcp-rubber-duckManual Installation
npx -y mcp-rubber-duckConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Rubber Duck
MCP Rubber Duck is an MCP server that acts as a bridge to query multiple LLMs simultaneously — both OpenAI-compatible HTTP APIs (OpenAI, Gemini, Groq, Perplexity, Ollama, Azure OpenAI, and more) and CLI coding agents (Claude Code, Codex, Gemini CLI, Aider). Just like rubber duck debugging, it lets you explain your problem to various AI 'ducks' and get diverse perspectives. Advanced features include consensus voting, LLM-as-judge evaluation, structured debates (Oxford, Socratic, adversarial), iterative refinement, and MCP Bridge to give ducks access to other MCP servers.
Prerequisites
- Node.js 20 or higher installed
- At least one API key for an HTTP provider (OPENAI_API_KEY, GEMINI_API_KEY, or GROQ_API_KEY) OR a CLI agent (Claude Code, Codex, Gemini CLI) installed locally
- An MCP-compatible client such as Claude Desktop, Cursor, or VS Code with MCP support
Install the package
Install mcp-rubber-duck globally from npm, or plan to run it directly via npx in your MCP client configuration.
npm install -g mcp-rubber-duckConfigure provider API keys
Set environment variables for the LLM providers you want to use as ducks. At minimum, set one of the following. You can also configure CLI agents like Claude Code by installing them locally.
export OPENAI_API_KEY=sk-...
export GEMINI_API_KEY=AI...
export GROQ_API_KEY=gsk_...Add to your MCP client configuration
Add mcp-rubber-duck to your claude_desktop_config.json, passing your API keys as environment variables so the server can authenticate with LLM providers.
{
"mcpServers": {
"rubber-duck": {
"command": "npx",
"args": ["-y", "mcp-rubber-duck"],
"env": {
"OPENAI_API_KEY": "sk-...",
"GEMINI_API_KEY": "AI...",
"DEFAULT_PROVIDER": "openai"
}
}
}
}Verify available ducks
After starting your MCP client, use the list_ducks tool to confirm which providers are configured and healthy before starting a session.
Optionally enable CLI agent ducks
To use local CLI coding agents as ducks, set the corresponding environment variable and ensure the agent is installed. For example, to enable Claude Code as a duck:
export CLI_CLAUDE_ENABLED=trueRubber Duck Examples
Client configuration
Configure Claude Desktop to use MCP Rubber Duck with OpenAI and Gemini as available ducks.
{
"mcpServers": {
"rubber-duck": {
"command": "npx",
"args": ["-y", "mcp-rubber-duck"],
"env": {
"OPENAI_API_KEY": "sk-your-openai-key",
"GEMINI_API_KEY": "your-gemini-key",
"DEFAULT_PROVIDER": "openai",
"LOG_LEVEL": "info"
}
}
}
}Prompts to try
Example prompts that use the rubber duck tools to get multiple AI perspectives and run structured debates.
- "Ask the openai duck: what's the best approach for implementing rate limiting in a Node.js API?"
- "Compare what openai and gemini think about using microservices vs. a monolith for a startup"
- "Have all configured ducks vote on whether to use REST or GraphQL for this API"
- "Run a Socratic debate between two ducks about the tradeoffs of eventual consistency"
- "List all available ducks and their current health status"
- "Chat with the groq duck about my authentication bug — here's the stack trace: [paste trace]"Troubleshooting Rubber Duck
list_ducks shows a provider as unhealthy or unavailable
Verify the API key for that provider is correctly set in the env block of your MCP config. Check the key has not expired and has sufficient quota. Use LOG_LEVEL=debug to see detailed error messages from the provider.
CLI duck (Claude Code, Codex) not appearing in list_ducks
Set CLI_CLAUDE_ENABLED=true (or CLI_CODEX_ENABLED=true) in your environment. Confirm the CLI agent binary is installed and accessible on your PATH by running 'which claude' or 'which codex' in your terminal.
npx -y mcp-rubber-duck fails with 'package not found' error
Run 'npm install -g mcp-rubber-duck' first to install the package globally. Alternatively, verify your npm registry is reachable and Node.js 20+ is installed with 'node --version'.
Frequently Asked Questions about Rubber Duck
What is Rubber Duck?
Rubber Duck is a Model Context Protocol (MCP) server that mcp server that acts as a bridge to query multiple openai-compatible llms with mcp tool access. just like rubber duck debugging, explain your problems to various ai 'ducks' who can actually research and get different perspectives! It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Rubber Duck?
Install via npm with the command: npx -y mcp-rubber-duck. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).
Which AI clients work with Rubber Duck?
Rubber Duck works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Rubber Duck free to use?
Yes, Rubber Duck is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
Rubber Duck Alternatives — Similar Coding Agents Servers
Looking for alternatives to Rubber Duck? Here are other popular coding agents servers you can use with Claude, Cursor, and VS Code.
Dify
★ 142.2kProduction-ready platform for agentic workflow development.
Ruflo
★ 54.0k🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, self-learning swarm intelligence, RAG integrat
Goose
★ 45.7kan open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
Antigravity Awesome Skills
★ 38.3kInstallable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.
AgentScope
★ 25.5kBuild and run agents you can see, understand and trust.
Serena
★ 24.5kA coding agent toolkit that provides IDE-like semantic code retrieval and editing tools, enabling LLMs to efficiently navigate and modify codebases using symbol-level operations instead of basic file reading and string replacements.
Browse More Coding Agents MCP Servers
Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Rubber Duck in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Rubber Duck?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.