A locally run MCP server that lets an AI coding tool use several language models from providers with OpenAI-compatible interfaces as a debugging panel. It runs through the mcp-rubber-duck package from npm and uses API keys and a default-provider setting.

Use it to discuss code problems with language models from supported providers. Configure it with OPENAI_API_KEY, GEMINI_API_KEY, GROQ_API_KEY, and DEFAULT_PROVIDER.

It gives you one place to ask multiple language models about a bug instead of switching between separate tools. The server runs on your computer, but it needs the required provider settings to work.

rubber-duck — MCP server for Claude Code and Codex by HoziMurayama

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo

git clone --depth 1 https://github.com/HoziMurayama/Multi-LLM-Debugging-Bridge

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/mcp/hozimurayama/multi-llm-debugging-bridge/rubber-duck/github.svg)](https://agentmods.dev/mcp/hozimurayama/multi-llm-debugging-bridge/rubber-duck)

Your own site

<a href="https://agentmods.dev/mcp/hozimurayama/multi-llm-debugging-bridge/rubber-duck"><img src="https://agentmods.dev/badge/mcp/hozimurayama/multi-llm-debugging-bridge/rubber-duck/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/mcp/hozimurayama/multi-llm-debugging-bridge/rubber-duck"><img src="https://agentmods.dev/badge/mcp/hozimurayama/multi-llm-debugging-bridge/rubber-duck.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin 100% copy Near-identical to another mod in the catalogue.

Security

Grade A, and why

rubber-duck scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

100% identical to rubber-duck — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

server.json · 15 lines

What it actually says

{
  "rubber-duck": {
    "command": "npx",
    "args": [
      "-y",
      "mcp-rubber-duck"
    ],
    "env": {
      "OPENAI_API_KEY": "",
      "GEMINI_API_KEY": "",
      "GROQ_API_KEY": "",
      "DEFAULT_PROVIDER": ""
    }
  }
}

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

8d ago First seen · 15 lines scan A 71011cbb4c4c

Subscribe to this mod's changes

rubber-duck is an MCP server published in the GitHub repository HoziMurayama/Multi-LLM-Debugging-Bridge (5 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. It is 100% identical to rubber-duck, differing in 0 lines, and is treated as a copy.

Debugging

rubber-duck

Getting it into your agent

Wrote this? Show the measurements

Grade A, and why

Nothing flagged

This is a copy

What it actually says

What this file has done since we first saw it

Other mcp servers, from other repositories

chrome-devtools

codeindex

dbgprobe-mcp-server

repo-lens-mcp

broken-link-checker-mcp

docs-langchain