Skip to main content
Glama

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!

npm version Docker Image MCP Registry

Why direct provider integration? MCP's sampling primitive -- a server borrowing the host's model -- was deprecated in the 2026-07-28 spec RC 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)

  • 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)

  • Guardrails -- Pluggable safety layer with rate limiting, token limits, pattern blocking, and PII redaction (docs)

  • 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)

  • 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)

Related MCP server: mcp-llm

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 for full setup and configuration.

Quick Start

# 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. Using Cursor, VS Code, Windsurf, or another tool? See the Setup Guide.

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

npm install -g mcp-rubber-duck

Install from Source

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

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. 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 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.

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.

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.

Usage Stats

Usage analytics with summary cards, provider breakdown with expandable rows, token distribution bars, and estimated costs.

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

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

Development

npm run dev        # Development with watch mode
npm test           # Run all tests
npm run lint       # ESLint
npm run typecheck  # Type check without emit

Documentation

Topic

Link

Setup guide (all tools)

docs/setup.md

Full configuration reference

docs/configuration.md

Claude Desktop setup

docs/claude-desktop.md

All tools with schemas

docs/tools.md

Prompt templates

docs/prompts.md

CLI coding agents

docs/cli-providers.md

MCP Bridge

docs/mcp-bridge.md

Guardrails

docs/guardrails.md

Docker deployment

docs/docker.md

Provider-specific setup

docs/provider-setup.md

Usage examples

docs/usage-examples.md

Architecture

docs/architecture.md

Roadmap

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).

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 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 to get started.

Quick start for contributors:

  1. Fork the repository

  2. Create a feature branch

  3. Follow our conventional commit guidelines

  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 for a detailed history of changes and releases.

Registry & Directory

Support


Happy Debugging with your AI Duck Panel!

Available Tools

12 tools
ask_duckAsk a DuckC
Read-only

Ask a question to a specific LLM provider (duck)

Inputs: prompt (required), model, images, provider, +1 more.

chat_with_duckChat with a DuckA

Have a conversation with a duck, maintaining context across messages

Inputs: message (required), conversation_id (required), model, images, +1 more.

clear_conversationsClear ConversationsA
DestructiveIdempotent

Clear all conversation history and start fresh

Inputs: no named parameters.

compare_ducksCompare DucksB
Read-only

Ask the same question to multiple ducks simultaneously

Inputs: prompt (required), model, images, providers. Returns: responses

duck_councilDuck CouncilC
Read-only

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

Inputs: prompt (required), model, images.

duck_debateDuck DebateB
Read-only

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

Inputs: format (required), prompt (required), rounds, providers, +1 more. Returns: topic, format, rounds, synthesis, +3 more

duck_iterateDuck IterationB
Read-only

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

Inputs: mode (required), prompt (required), providers (required), iterations.

duck_judgeDuck JudgeA
Read-only

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

Inputs: responses (required), judge, persona, criteria.

duck_voteDuck VoteB
Read-only

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

Inputs: options (required), question (required), voters, require_reasoning. Returns: isTie, tally, votes, winner, +6 more

get_usage_statsUsage StatisticsA
Read-only

Get usage statistics for a time period. Shows token counts and costs (when pricing configured).

Inputs: period. Returns: usage, period, totals, endDate, +2 more

list_ducksList DucksB
Read-only

List all available LLM providers (ducks) and their status

Inputs: check_health.

list_modelsList ModelsB
Read-only

List available models for LLM providers

Inputs: provider, fetch_latest.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.2/5.0

    Scored across 12 tools

    Disambiguation3/5

    Most tools target distinct actions, but compare_ducks and duck_council both send the same question to multiple providers and could be confused. The orchestration tools duck_vote, duck_judge, duck_iterate, and duck_debate are differentiated by their descriptions, though the boundaries remain somewhat subtle.

    Naming Consistency3/5

    About half the tools follow a clear verb_noun pattern (list_ducks, ask_duck, chat_with_duck, compare_ducks, get_usage_stats), while the multi-duck orchestration tools use duck_<verb> nouns (duck_council, duck_vote, duck_judge, duck_iterate, duck_debate). The duck-themed naming is readable but the two conventions are mixed.

    Tool Count5/5

    The 12 tools are well within the appropriate range for a multi-provider LLM orchestration server. Each tool appears to cover a distinct workflow such as listing, chatting, comparing, voting, judging, iterating, debating, or usage reporting.

    Completeness4/5

    The surface covers provider/model listing, one-shot and contextual chat, several multi-duck orchestration modes, conversation clearing, and usage statistics. Minor gaps exist around managing individual conversations or configuring provider/model selection per request, but core workflows are covered.

    Maintenance

    ActivityMaintained
    ResponsivenessLimited data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      B
      quality
      D
      maintenance
      This MCP server utilizes DuckDuckGo for web searches, providing structured search results with metadata and features like smart content classification and language detection, facilitating easy integration with AI clients supporting the MCP protocol.
      1
      59 npm
      2
      MIT