mcp-rubber-duck
An MCP server that acts as a bridge to query multiple OpenAI-compatible LLMs with MCP tool access. Just like rubber duck debugging, explain your problems to various AI "ducks" who can actually research and get different perspectives!
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Check it deeper on your machine
It has changed since its scan on 11 Nov 2026.
As a Claude Code plugin, install it and then ask Claude Code:
/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/nesquikm/mcp-rubber-duck with scanskillsafety
Or from a terminal, clone it and run it:
git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/nesquikm/mcp-rubber-duck'
It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.
Badge for your README
Markdown
[](/listings/nesquikm--mcp-rubber-duck)HTML
<a href="/listings/nesquikm--mcp-rubber-duck"><img src="/api/listings/nesquikm--mcp-rubber-duck/badge.svg" alt="findsafeskills safety rating" /></a>Install
Install instructions from the README
As written by the repo's author. findsafeskills has not verified these steps.
# Install globally npm install -g mcp-rubber-duck # Or use npx directly in Claude Desktop config npx mcp-rubber-duck
**Using Claude Desktop?** Jump to [Claude Desktop Configuration](./docs/claude-desktop.md). **Using Cursor, VS Code, Windsurf, or another tool?** See the [Setup Guide](./docs/setup.md).
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
README.md · README · 292 lines
View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)
This file has changed since it was scanned, so this is not exactly the text that was scanned, and no line is marked. The findings are listed with the safety scan above.
- # MCP Rubber Duck
- An MCP (Model Context Protocol) server that acts as a bridge to query multiple LLMs -- both OpenAI-compatible HTTP APIs and CLI coding agents. Just like rubber duck debugging, explain your problems to various AI "ducks" and get different perspectives!
- [](https://www.npmjs.com/package/mcp-rubber-duck)
- [](https://github.com/nesquikm/mcp-rubber-duck/pkgs/container/mcp-rubber-duck)
- [](https://registry.modelcontextprotocol.io)
- <p align="center">
- <img src="assets/mcp-rubber-duck.jpg" alt="MCP Rubber Duck - AI ducks helping debug code" width="600">
- </p>
- > **Why direct provider integration?** MCP's `sampling` primitive -- a server borrowing the *host's* model -- was deprecated in the [2026-07-28 spec RC](https://github.com/modelcontextprotocol/modelcontextprotocol/pull/2577) in favor of servers integrating directly with LLM provider APIs. Rubber Duck has always worked this way (it brings its own ducks), so it's aligned with where the protocol is heading -- no migration required.
- ## Features
- - **Universal OpenAI Compatibility** -- Works with any OpenAI-compatible API endpoint
- - **CLI Agent Support** -- Use CLI coding agents (Claude Code, Codex, Gemini CLI, Grok, Aider) as ducks
- - **Multiple Ducks** -- Configure and query multiple LLM providers simultaneously
- - **Conversation Management** -- Maintain context across multiple messages
- - **Duck Council** -- Get responses from all your configured LLMs at once
- - **Consensus Voting** -- Multi-duck voting with reasoning and confidence scores
- - **LLM-as-Judge** -- Have ducks evaluate and rank each other's responses
- - **Iterative Refinement** -- Two ducks collaboratively improve responses
- - **Structured Debates** -- Oxford, Socratic, and adversarial debate formats
- - **MCP Prompts** -- 8 reusable prompt templates for multi-LLM workflows
- - **Vision Input** -- Send images alongside prompts to vision-capable models ([docs](./docs/tools.md#vision-input))
- - **Automatic Failover** -- Falls back to other providers if primary fails
- - **Health Monitoring** -- Real-time health checks for all providers
- - **Usage Tracking** -- Track requests, tokens, and estimated costs per provider
- - **MCP Bridge** -- Connect ducks to other MCP servers for extended functionality ([docs](./docs/mcp-bridge.md))
- - **Guardrails** -- Pluggable safety layer with rate limiting, token limits, pattern blocking, and PII redaction ([docs](./docs/guardrails.md))
- - **Granular Security** -- Per-server approval controls with session-based approvals
- - **Interactive UIs** -- Rich HTML panels for compare, vote, debate, and usage tools (via [MCP Apps](https://github.com/modelcontextprotocol/ext-apps))
- - **Tool Annotations** -- MCP-compliant hints for tool behavior (read-only, destructive, etc.)
- - **Structured Output** -- `outputSchema` on tools returning structured JSON for client-side validation (Cursor, VS Code/Copilot)
- - **Spec-Aligned by Design** -- connects directly to provider APIs, the path the MCP `2026-07-28` spec recommends now that server-side `sampling` is deprecated ([SEP-2577](https://github.com/modelcontextprotocol/modelcontextprotocol/pull/2577))
- ## Supported Providers
- ### HTTP Providers (OpenAI-compatible API)
- Any provider with an OpenAI-compatible API endpoint, including:
- - **OpenAI**
- - **Google Gemini**
- - **Anthropic** (via OpenAI-compatible endpoints)
- - **Groq** (fast inference for open-weight models)
- - **Together AI** (broad open-weight model catalog)
- - **Perplexity** (online models with web search)
- - **Azure OpenAI**, **Ollama**, **LM Studio**, **Custom**
- ### CLI Providers (Coding Agents)
- Command-line coding agents that run as local processes:
- - **Claude Code** (`claude`) -- **Codex** (`codex`) -- **Gemini CLI** (`gemini`) -- **Grok CLI** (`grok`) -- **Aider** (`aider`) -- **Custom**
- See [CLI Providers](./docs/cli-providers.md) for full setup and configuration.
- ## Quick Start
- ```bash
- # Install globally
- npm install -g mcp-rubber-duck
- # Or use npx directly in Claude Desktop config
- npx mcp-rubber-duck
- ```
- **Using Claude Desktop?** Jump to [Claude Desktop Configuration](./docs/claude-desktop.md).
- **Using Cursor, VS Code, Windsurf, or another tool?** See the [Setup Guide](./docs/setup.md).
- ## Installation
- ### Prerequisites
- - Node.js 20 or higher
- - npm or yarn
- - At least one API key for an HTTP provider, **or** a CLI coding agent installed locally
- ### Install from NPM
- ```bash
- npm install -g mcp-rubber-duck
- ```
- ### Install from Source
- ```bash
- git clone https://github.com/nesquikm/mcp-rubber-duck.git
- cd mcp-rubber-duck
- npm install
- npm run build
- npm start
- ```
- ## Configuration
- Create a `.env` file or `config/config.json`. Key environment variables:
- | Variable | Description |
- |----------|-------------|
- | `OPENAI_API_KEY` | OpenAI API key |
- | `GEMINI_API_KEY` | Google Gemini API key |
- | `GROQ_API_KEY` | Groq API key |
- | `OPENAI_DEFAULT_MODEL` | OpenAI model (default: `gpt-5.4`) |
- | `GEMINI_DEFAULT_MODEL` | Gemini model (default: `gemini-3.8-flash`) |
- | `GROQ_DEFAULT_MODEL` | Groq model (default: `openai/gpt-oss-120b`) |
- | `DEFAULT_PROVIDER` | Default provider key: `openai`, `google`, `groq`, `ollama`, or a custom name |
- | `DEFAULT_TEMPERATURE` | Default temperature (e.g., `0.7`) |
- | `LOG_LEVEL` | `debug`, `info`, `warn`, `error` |
- | `MCP_SERVER` | Set to `true` for MCP server mode |
- | `MCP_BRIDGE_ENABLED` | Enable MCP Bridge (ducks access external MCP servers) |
- | `CUSTOM_{NAME}_*` | Custom HTTP providers |
- | `CLI_{AGENT}_ENABLED` | Enable CLI agents (`CLAUDE`, `CODEX`, `GEMINI`, `GROK`, `AIDER`) |
- Full reference: **[Configuration docs](./docs/configuration.md)**
- ## Interactive UIs (MCP Apps)
- Four tools -- `compare_ducks`, `duck_vote`, `duck_debate`, and `get_usage_stats` -- can render rich interactive HTML panels inside supported MCP clients via [MCP Apps](https://github.com/modelcontextprotocol/ext-apps). Once this MCP server is configured in a supporting client, the UIs appear automatically -- no additional setup is required. Clients without MCP Apps support still receive the same plain text output (no functionality is lost). See the [MCP Apps repo](https://github.com/modelcontextprotocol/ext-apps) for an up-to-date list of supported clients.
- ### Compare Ducks
- Compare multiple model responses side-by-side, with latency indicators, token counts, model badges, and error states.
- <p align="center">
- <img src="assets/ext-apps-compare.png" alt="Compare Ducks interactive UI" width="600">
- </p>
- ### Duck Vote
- Have multiple ducks vote on options, displayed as a visual vote tally with bar charts, consensus badge, winner card, confidence bars, and collapsible reasoning.
- <p align="center">
- <img src="assets/ext-apps-vote.png" alt="Duck Vote interactive UI" width="600">
- </p>
- ### Duck Debate
- Structured multi-round debate between ducks, shown as a round-by-round view with format badge, participant list, collapsible rounds, and synthesis section.
- <p align="center">
- <img src="assets/ext-apps-debate.png" alt="Duck Debate interactive UI" width="600">
- </p>
- ### Usage Stats
- Usage analytics with summary cards, provider breakdown with expandable rows, token distribution bars, and estimated costs.
- <p align="center">
- <img src="assets/ext-apps-usage-stats.png" alt="Usage Stats interactive UI" width="600">
- </p>
- ## Available Tools
- | Tool | Description |
- |------|-------------|
- | `ask_duck` | Ask a single question to a specific LLM provider |
- | `chat_with_duck` | Conversation with context maintained across messages |
- | `clear_conversations` | Clear all conversation history |
- | `list_ducks` | List configured providers and health status |
- | `list_models` | List available models for providers |
- | `compare_ducks` | Ask the same question to multiple providers simultaneously |
- | `duck_council` | Get responses from all configured ducks |
- | `get_usage_stats` | Usage statistics and estimated costs |
- | `duck_vote` | Multi-duck voting with reasoning and confidence |
- | `duck_judge` | Have one duck evaluate and rank others' responses |
- | `duck_iterate` | Iteratively refine a response between two ducks |
- | `duck_debate` | Structured multi-round debate between ducks |
- | `mcp_status` | MCP Bridge status and connected servers |
- | `get_pending_approvals` | Pending MCP tool approval requests |
- | `approve_mcp_request` | Approve or deny a duck's MCP tool request |
- Full reference with input schemas: **[Tools docs](./docs/tools.md)**
- ## Available Prompts
- | Prompt | Purpose | Required Arguments |
- |--------|---------|-------------------|
- | `perspectives` | Multi-angle analysis with assigned lenses | `problem`, `perspectives` |
- | `assumptions` | Surface hidden assumptions in plans | `plan` |
- | `blindspots` | Hunt for overlooked risks and gaps | `proposal` |
- | `tradeoffs` | Structured option comparison | `options`, `criteria` |
- | `red_team` | Security/risk analysis from multiple angles | `target` |
- | `reframe` | Problem reframing at different levels | `problem` |
- | `architecture` | Design review across concerns | `design`, `workloads`, `priorities` |
- | `diverge_converge` | Divergent exploration then convergence | `challenge` |
- Full reference with examples: **[Prompts docs](./docs/prompts.md)**
- ## Development
- ```bash
- npm run dev # Development with watch mode
- npm test # Run all tests
- npm run lint # ESLint
- npm run typecheck # Type check without emit
- ```
- ## [Documentation](./docs/README.md)
- | Topic | Link |
- |-------|------|
- | **Setup guide (all tools)** | **[docs/setup.md](./docs/setup.md)** |
- | Full configuration reference | [docs/configuration.md](./docs/configuration.md) |
- | Claude Desktop setup | [docs/claude-desktop.md](./docs/claude-desktop.md) |
- | All tools with schemas | [docs/tools.md](./docs/tools.md) |
- | Prompt templates | [docs/prompts.md](./docs/prompts.md) |
- | CLI coding agents | [docs/cli-providers.md](./docs/cli-providers.md) |
- | MCP Bridge | [docs/mcp-bridge.md](./docs/mcp-bridge.md) |
- | Guardrails | [docs/guardrails.md](./docs/guardrails.md) |
- | Docker deployment | [docs/docker.md](./docs/docker.md) |
- | Provider-specific setup | [docs/provider-setup.md](./docs/provider-setup.md) |
- | Usage examples | [docs/usage-examples.md](./docs/usage-examples.md) |
- | Architecture | [docs/architecture.md](./docs/architecture.md) |
- | Roadmap | [docs/roadmap.md](./docs/roadmap.md) |
- ## Troubleshooting
- ### Provider Not Working
- 1. Check API key is correctly set
- 2. Verify endpoint URL is correct
- 3. Run health check: `list_ducks({ check_health: true })`
- 4. Check logs for detailed error messages
- ### OpenAI gpt-5.6 / gpt-6 Models Fail With the MCP Bridge
- OpenAI's Chat Completions API rejects function tools for the gpt-5.6 and gpt-6 families (`400 Function tools with reasoning_effort are not supported ... use /v1/responses`). They work for plain calls, but with `MCP_BRIDGE_ENABLED=true` the ducks attach tools and those requests fail. Use `gpt-5.4` (the default) or `gpt-5.4-mini` until Responses API support lands ([#166](https://github.com/nesquikm/mcp-rubber-duck/issues/166)).
- ### Connection Issues
- - For local providers (Ollama, LM Studio), ensure they're running
- - Check firewall settings for local endpoints
- - Verify network connectivity to cloud providers
- ### Rate Limiting
- - Configure failover to alternate providers
- - Adjust `max_retries` and `timeout` settings
- - See [Guardrails](./docs/guardrails.md) for rate limiting configuration
- ## Contributing
- ```
- __
- <(o )___
- ( ._> /
- `---' Quack! Ready to debug!
- ```
- We love contributions! Whether you're fixing bugs, adding features, or teaching our ducks new tricks, we'd love to have you join the flock.
- Check out our [Contributing Guide](./CONTRIBUTING.md) to get started.
- **Quick start for contributors:**
- 1. Fork the repository
- 2. Create a feature branch
- 3. Follow our [conventional commit guidelines](./CONTRIBUTING.md#commit-messages-duck-communication-protocol)
- 4. Add tests for new functionality
- 5. Submit a pull request
- ## License
- MIT License - see LICENSE file for details
- ## Acknowledgments
- - Inspired by the rubber duck debugging method
- - Built on the Model Context Protocol (MCP)
- - Uses OpenAI SDK for HTTP provider compatibility
- - Supports CLI coding agents (Claude Code, Codex, Gemini CLI, Grok, Aider)
- ## Changelog
- See [CHANGELOG.md](./CHANGELOG.md) for a detailed history of changes and releases.
- ## Registry & Directory
- - **NPM Package**: [npmjs.com/package/mcp-rubber-duck](https://www.npmjs.com/package/mcp-rubber-duck)
- - **Docker Images**: [ghcr.io/nesquikm/mcp-rubber-duck](https://github.com/nesquikm/mcp-rubber-duck/pkgs/container/mcp-rubber-duck)
- - **MCP Registry**: Official MCP server `io.github.nesquikm/rubber-duck`
- - **Glama Directory**: [glama.ai/mcp/servers/@nesquikm/mcp-rubber-duck](https://glama.ai/mcp/servers/@nesquikm/mcp-rubber-duck)
- - **Awesome MCP Servers**: Listed in the [community directory](https://github.com/punkpeye/awesome-mcp-servers)
- ## Support
- - Report issues: https://github.com/nesquikm/mcp-rubber-duck/issues
- - Documentation: https://github.com/nesquikm/mcp-rubber-duck/wiki
- - Discussions: https://github.com/nesquikm/mcp-rubber-duck/discussions
- ---
- Happy Debugging with your AI Duck Panel!
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.