# MCP Rubber Duck

> MCP Rubber Duck — hozimurayama-multi-llm-debugging-bridge. Use this tool when you need to bridge multiple Large Language Models (LLMs) for collaborative debugging and diverse AI perspectives. It solves problems of limited viewpoints and debugging capabilities by connecting OpenAI-compatible APIs and CLI coding agents, providing a unified interface for inputs and outputs. This tool is ideal for use cases requiring multi-model collaboration, such as complex coding projects or nuanced language understanding tasks.

Canonical page: https://skillsregistry.net/skills/hozimurayama-multi-llm-debugging-bridge  
JSON: https://api.skillsregistry.net/v1/skills/hozimurayama-multi-llm-debugging-bridge

## Description

An MCP server that bridges multiple LLMs (OpenAI-compatible APIs and CLI coding agents) for collaborative debugging and diverse AI perspectives.

## Trust

- **Trust score (0–1):** 0.56
- **Verification tier:** scanned
- **Last scanned:** 2026-08-29

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-08-29

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/irbhmvkz5l)
- **Repository:** <https://github.com/HoziMurayama/Multi-LLM-Debugging-Bridge>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "hozimurayama-multi-llm-debugging-bridge"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/hozimurayama-multi-llm-debugging-bridge` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/hozimurayama-multi-llm-debugging-bridge/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt