mcp-rubber-duck

Ask a question to a specific LLM provider (duck)

Have a conversation with a duck, maintaining context across messages

Clear all conversation history and start fresh

List all available LLM providers (ducks) and their status

List available models for LLM providers

Ask the same question to multiple ducks simultaneously

Get responses from all configured ducks (like a panel discussion)

Have multiple ducks vote on options with reasoning. Returns vote tally, confidence scores, and consensus level.

Have one duck evaluate and rank other ducks' responses. Use after duck_council to get a comparative evaluation.

Iteratively refine a response between two ducks. One generates, the other critiques/improves, alternating for multiple rounds.

Structured multi-round debate between ducks. Supports oxford (pro/con), socratic (questioning), and adversarial (attack/defend) formats.