Rubber Duck
Bridge to multiple OpenAI-compatible LLMs with consensus voting and multi-provider querying
Bridges to multiple OpenAI-compatible LLM providers including OpenAI, Google Gemini, Groq, Together AI, Perplexity, and Ollama. Features a duck council that queries all configured LLMs simultaneously, consensus voting with reasoning and confidence scores, and LLM-as-Judge evaluation where models rank each other's responses. Supports conversation management, response caching, and automatic failover.
Source
Repository: https://github.com/nesquikm/mcp-rubber-duck
Maintain Rubber Duck?
Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.
[Rubber Duck on getagentictools](https://getagentictools.com/mcp/nesquikm-mcp-rubber-duck?ref=badge) Related mcp
Engram Provides a persistent identity layer for AI tools with tools for user profiles, lessons, and decisions.
LM Studio Bridges Claude with locally running LLM models via LM Studio, enabling users to leverage private models through Claude's interface
ProjectMem Local-first memory and judgment layer for AI coding agents with pre-commit warnings and cross-project lesson tracking.
MIMO Image Recognition Image understanding via Xiaomi's MIMO multimodal model, supporting local paths, URLs, and multiple images.
Chiasmus Formal verification via Z3 SMT solver and Tau Prolog with source code call graph analysis.
UTCP Bridge UTCP-MCP Bridge is a universal, all-in-one MCP server that brings the full power of the Universal Tool Calling Protocol (UTCP) to