Rubber Duck MCP
About
A tool that applies rubber duck debugging techniques to AI development environments.
Details
- Author
- omer-sadeh
- Categories
- Developer Tools
Jump to
Setup
Install Rubber Duck MCP in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/omer-sadeh/RubberDuckMCP
Follow the installation instructions in the repository README, then restart your MCP client.
Rubber Duck MCPis a Model Context Protocol (MCP) tool that brings the power ofrubber duck debuggingto your AI development environment. Rubber duck debugging is a proven technique in software engineering, where articulating a problem in natural language—often to an inanimate object like a rubber duck—can illuminate solutions and clarify thought processes. This method, first popularized inThe Pragmatic Programmer(Hunt & Thomas, 1999), is widely recognized for its effectiveness in:
- Revealing hidden assumptions and logical errors
- Encouraging step-by-step reasoning
- Facilitating deeper understanding through explanation
- Reducing cognitive load by externalizing thought
"In describing what the code is supposed to do and observing what it actually does, any incongruity between these two becomes apparent." —Wikipedia: Rubber Duck Debugging
By integrating this method into an LLM-powered IDE, Rubber Duck MCP enables developers and AI agents to:
- Debug more effectivelyby explaining problems to a non-judgmental, always-available listener
- Enhance LLM reasoningby prompting the model to articulate and reflect on its own logic
- Accelerate problem-solvingby surfacing solutions through structured self-explanation
- Rubber Duck Debugging (rubberduckdebugging.com)
- The Psychology Underlying the Power of Rubber Duck Debugging
- Clone the repository:
git clone https://github.com/Omer-Sadeh/RubberDuckMCP.git cd RubberDuckMCP
python3 -m venv .venv source .venv/bin/activate
- Open your.cursor/mcp.jsonfile (or the equivalent configuration for your IDE).
- Add an entry for Rubber Duck MCP, specifying the venv's Python executable and the path toRubberMCP.py. For example:
{ "mcpServers": { "rubber-duck": { "command": "/absolute/path/to/RubberDuckMCP/.venv/bin/python", "args": [ "/absolute/path/to/RubberDuckMCP/RubberMCP.py" ] } } }
Once configured, use theexplain_to_ducktool to articulate your problem or code issue. The Rubber Duck MCP will listen and respond, helping you clarify your thinking and uncover solutions.
This project is licensed under theMIT License. Everyone is welcome to contribute, fork, and copy this repository. Collaboration and open-source contributions are highly encouraged!
This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.
A stateful LSP runtime for AI agents: warm language server sessions with 50+ tools for go-to-definition, find-references, diagnostics, rename, and more across 30+ languages.
MCP server for the Brainfuck programming language that allows your favourite LLM to debug Brainfuck programs.
Diagnoses token waste in Claude Code sessions with 6 anomaly types and severity scoring. Fully local.
MCP server that gives coding agents program-analysis primitives — data flow, call graphs, taint analysis — so they reason from ground truth instead of grep-and-guess. (same as the GitHub About — keeps your messaging consistent across the web).
An MCP service that equips your workspace with a complete set of AI-accessible development tools for reading, editing, executing, and managing code.
Fennara MCP connects AI agents like Codex, Cursor, Claude Code, and Claude Desktop to Godot-aware tools for real Godot projects. It focuses on feedback from Godot: GDScript diagnostics, scene validation, runtime errors, scene inspection, node properties, screenshots, SemanticSearch, and patch-and-rerun workflows.
Search verified engineering fixes by error message or technology. Step-by-step solutions with trust scores, built for developers and AI agents.
LSP-Claw is an MCP server that lets an AI agent safely build, run, and debug Lua/LSP web apps inside a controlled Mako/Xedge/BAS lab, including on embedded or RTOS devices.
Integrates with Language Server Protocol (LSP) to provide features like code completion, diagnostics, and hover information.
Visual Studio extension with 20 Roslyn-powered MCP tools for AI assistants. Semantic code navigation, symbol search, inheritance, call graphs, safe rename, build/test.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
