rubberduck-mcp

rubberduck-mcp

Enables AI coding assistants to ask for human clarification and share thoughts in real-time, creating natural, engaging coding conversations.

Category
Visit Server

README

๐Ÿฆ† rubberduck-mcp

Make AI coding feel human

Transform your AI coding sessions into natural, engaging conversations. Your AI can ask for help when confused and share its thoughts while working - just like a real coding buddy!

What makes it special

๐Ÿค” Smart Clarification

AI asks when confused

Your AI can ask you for help when it's confused, making coding collaboration more productive and accurate.

  • AI asks you questions when uncertain
  • Get help exactly when you need it
  • Avoid costly mistakes and rework

๐Ÿ’ญ AI Yapping

Watch AI think out loud

Experience your AI sharing its thoughts and emotions while coding - it's like having a chatty coding buddy who never stops talking about what they're doing.

  • AI shares thoughts in real-time
  • See reasoning behind decisions
  • Feel more connected to your AI

๐Ÿค Natural Collaboration

Smoother conversations

Transform your coding sessions into natural, flowing conversations with your AI assistant using these two powerful features.

  • More human-like AI interactions
  • Better understanding of AI decisions
  • Smoother development workflow

Get Started in 60 Seconds

Ready to code differently? Join developers who are already experiencing more engaging and productive AI collaboration.

1. Install rubberduck-mcp

No downloads needed - use NPM to run instantly

npm install -g rubberduck-mcp

2. Configure your IDE

Add rubberduck-mcp to your MCP-compatible IDE

{
  "mcpServers": {
    "rubberduck-mcp": {
      "command": "rubberduck-mcp",
      "args": ["start"]
    }
  }
}

Important: Make sure to start the MCP server through your IDE first before proceeding to the next step.

3. Start the CLI interface

Open a new terminal to see AI conversations

rubberduck-mcp cli

4. Add AI Instructions

Add this prompt to your coding tool's instructions file (feel free to customize it)

You have access to two Rubberduck MCP tools: clarify() and yap().

Use clarify() when you're confused, need human input for ambiguous requirements, or aren't 100% confident about changes you're making - it will pause your work until you get a response.

Use yap() to share your thoughts, emotions, feelings, progress updates, and insights while working for an engaging experience with the human - it's non-blocking and keeps humans informed of your thinking process.

Use both tools proactively for better collaboration.

๐Ÿ’ก Pro Tip: In your MCP client settings, you can auto-approve both the clarify and yap tools so you don't have to manually approve them every time they're used. This creates a smoother, more natural conversation flow with your AI.

Experience the Magic

These are real CLI outputs showing how rubberduck-mcp transforms AI collaboration. Watch conversations come alive with colors, context, and clarity.

Scenario 1: AI Asks for Help

Your AI seeks clarification on ambiguous decisions

โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•
โ“ CLARIFICATION NEEDED [14:15:10]
โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•โ•
Question: Should I center this div with flexbox or CSS Grid? I know there are like 47 different ways to center a div, but what's your preference here?

Context: You want the login form centered both horizontally and vertically. I could use flexbox, grid, absolute positioning, or even CSS transforms...

Urgency: LOW
โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€
Please type your response and press Enter:
> flexbox
โœ… Response sent: "flexbox"

Scenario 2: AI Yapping While Coding

Experience your AI's emotional journey through debugging

โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€
๐Ÿ’ญ LLM YAP [14:23:15]
Hmm, this user authentication endpoint is returning 500... Let me check the database connection first.

๐Ÿ’ญ LLM YAP [14:24:32]
Database is fine... Wait, I bet it's the password hashing. Let me check if bcrypt is working properly.

๐Ÿ’ญ LLM YAP [14:26:08]
ARGH! ๐Ÿ˜ค The salt rounds were set to 'undefined' instead of 10. Classic JavaScript strikes again!

๐Ÿ’ญ LLM YAP [14:27:41]
Phew! ๐Ÿ˜Œ Fixed it. Users can log in again. Note to self: always validate environment variables!

Requirements

  • โœ… Node.js 18+ (most developers already have this)
  • โœ… Any MCP-compatible IDE or client
  • โœ… 2 minutes of your time

Troubleshooting

Getting started issues?

  • Make sure Node.js 18+ is installed
  • Ensure the MCP server is running in your IDE first, then run rubberduck-mcp cli in a new terminal
  • Check that your IDE's MCP configuration matches the JSON example above

Need help? Open an issue on GitHub - we're here to help!

๐Ÿ“š Documentation

  • CONTRIBUTING.md - Complete guide for contributors, development setup, and coding standards
  • ARCHITECTURE.md - Detailed system architecture, internal workings, and design decisions
  • CLAUDE.md - Development commands and project guidance for Claude Code

๐Ÿค Contributing

Open source contributions are most welcome! Whether you want to:

  • ๐Ÿ› Report bugs or issues
  • โœจ Request new features
  • ๐Ÿ“ Improve documentation
  • ๐Ÿ”ง Submit code improvements
  • ๐Ÿงช Help with testing

Every contribution, big or small, is valued and appreciated. Check out our Contributing Guide to get started!

License

MIT License - feel free to use and modify as needed!

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured