Rubber Duck

Provides a rubber duck debugging MCP server to articulate problems and guide reasoning within an AI development workflow.

python

0

GitHub Stars

python

Language

4 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "omer-sadeh-rubberduckmcp": {
      "command": "/absolute/path/to/RubberDuckMCP/.venv/bin/python",
      "args": [
        "/absolute/path/to/RubberDuckMCP/RubberMCP.py"
      ]
    }
  }
}

Rubber Duck MCP enables you to debug and reason more clearly by articulating your problem to an always-available, non-judgmental listener. It exposes a focused, explicit workflow for explaining code issues and prompts the model to reflect on its own logic, helping you uncover solutions faster and with greater confidence.

How to use

After you configure the MCP client, you can engage the Rubber Duck listener by triggering the explain_to_duck tool. Describe the problem or code issue in natural language, and the Rubber Duck MCP will listen, respond with clarifying questions, and help surface potential solutions. Use this as part of your debugging and reasoning process to validate assumptions, incrementally reason through steps, and reveal hidden gaps in logic.

How to install

Prerequisites: You need Python 3.8 or higher and fastmcp installed via pip.

Steps to set up Rubber Duck MCP in your environment:

# 1. Clone the project
git clone https://github.com/Omer-Sadeh/RubberDuckMCP.git
cd RubberDuckMCP

# 2. Create and activate a virtual environment (recommended)
python3 -m venv .venv
source .venv/bin/activate

# 3. Install dependencies
pip install -r requirements.txt

# 4. Add Rubber Duck MCP to Cursor (or another MCP-supporting IDE)
# Create or modify the MCP configuration in your IDE to point to Rubber Duck MCP.
# Example configuration snippet is provided in the next section.

Configuration example and notes

Configure your MCP client to run Rubber Duck MCP as a local stdio server using your virtual environment’s Python executable and the RubberMCP.py script. This sets up a local, in-process MCP server that you can start and stop as part of your IDE workflow.

{
  "mcpServers": {
    "rubber_duck": {
      "command": "/absolute/path/to/RubberDuckMCP/.venv/bin/python",
      "args": [
        "/absolute/path/to/RubberDuckMCP/RubberMCP.py"
      ]
    }
  }
}

Security and notes

Run Rubber Duck MCP in a trusted environment since it may access and reflect on sensitive code explanations during debugging sessions. Restrict access to your development workspace and use standard secure practices for running local tools.

Troubleshooting

If the MCP server fails to start, double-check that the virtual environment is activated and that the paths in the configuration match your local setup. Ensure the Python executable exists at the specified path and that RubberMCP.py is present at the given location.

Available tools

explain_to_duck

Articulates the problem or code issue to a rubber duck listener, prompting the model to reflect on its own reasoning and surface potential solutions.