Schema | mcp-rubber-duck

mcp-rubber-duck

Describes the environment variables required to run the server.

Name	Required	Description	Default
`LOG_LEVEL`	No	Log level setting	info
`GROQ_API_KEY`	No	Your Groq API key
`GROQ_NICKNAME`	No	Optional: defaults to "Groq Duck"	Groq Duck
`CUSTOM_API_KEY`	No	Your custom provider API key
`GEMINI_API_KEY`	No	Your Google Gemini API key
`OPENAI_API_KEY`	No	Your OpenAI API key
`CUSTOM_BASE_URL`	No	Custom provider base URL
`CUSTOM_NICKNAME`	No	Optional: defaults to "Custom Duck"	Custom Duck
`GEMINI_NICKNAME`	No	Optional: defaults to "Gemini Duck"	Gemini Duck
`OLLAMA_BASE_URL`	No	Ollama base URL	http://localhost:11434/v1
`OLLAMA_NICKNAME`	No	Optional: defaults to "Local Duck"	Local Duck
`OPENAI_NICKNAME`	No	Optional: defaults to "GPT Duck"	GPT Duck
`DEFAULT_PROVIDER`	No	Default provider to use	openai
`TOGETHER_API_KEY`	No	Your Together AI API key
`GROQ_DEFAULT_MODEL`	No	Optional: defaults to llama-3.3-70b-versatile	llama-3.3-70b-versatile
`DEFAULT_TEMPERATURE`	No	Default temperature setting	0.7
`CUSTOM_DEFAULT_MODEL`	No	Optional: defaults to custom-model	custom-model
`GEMINI_DEFAULT_MODEL`	No	Optional: defaults to gemini-2.5-flash	gemini-2.5-flash
`OLLAMA_DEFAULT_MODEL`	No	Optional: defaults to llama3.2	llama3.2
`OPENAI_DEFAULT_MODEL`	No	Optional: defaults to gpt-4o-mini	gpt-4o-mini

Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.

This server publishes no instructions, or was last inspected before Glama recorded them.

Features and capabilities supported by this server

Protocol revision2025-11-25

Capability	Details
`tasks`	{ "list": {}, "cancel": {}, "requests": { "tools": { "call": {} } } }
`tools`	{ "listChanged": true }
`prompts`	{ "listChanged": true }
`resources`	{ "listChanged": true }

Functions exposed to the LLM to take actions

Name	Description
ask_duckB	Ask a question to a specific LLM provider (duck)
chat_with_duckA	Have a conversation with a duck, maintaining context across messages
clear_conversationsA	Clear all conversation history and start fresh
list_ducksA	List all available LLM providers (ducks) and their status
list_modelsA	List available models for LLM providers
compare_ducksA	Ask the same question to multiple ducks simultaneously
duck_councilA	Get responses from all configured ducks (like a panel discussion)
duck_voteC	Have multiple ducks vote on options with reasoning. Returns vote tally, confidence scores, and consensus level.
duck_judgeA	Have one duck evaluate and rank other ducks' responses. Use after duck_council to get a comparative evaluation.
duck_iterateA	Iteratively refine a response between two ducks. One generates, the other critiques/improves, alternating for multiple rounds.
duck_debateA	Structured multi-round debate between ducks. Supports oxford (pro/con), socratic (questioning), and adversarial (attack/defend) formats.
get_usage_statsA	Get usage statistics for a time period. Shows token counts and costs (when pricing configured).

Interactive templates invoked by user choice

Name	Description
`perspectives`	Analyze a problem from multiple perspectives. Each LLM adopts a different analytical lens (e.g., security, performance, UX) for comprehensive multi-angle analysis.
`assumptions`	Surface and challenge hidden assumptions in a plan, design, or idea. Identifies implicit premises that could be risky if wrong.
`blindspots`	Hunt for missing considerations, overlooked risks, and gaps in a proposal. Acts as a panel of critical reviewers looking for what might be underweighted.
`tradeoffs`	Compare options with explicit criteria and trade-off analysis. Provides structured evaluation to help make informed decisions.
`red_team`	Conduct attack surface analysis from multiple angles. Each reviewer focuses on different risk dimensions (security, privacy, abuse, compliance).
`reframe`	Reframe a problem from multiple angles and abstraction levels. Helps break out of mental ruts by viewing the problem differently.
`architecture`	Structured architecture or design review from multiple engineering perspectives. Each reviewer focuses on different cross-cutting concerns.
`diverge_converge`	Structure divergent thinking (explore many options) followed by convergence (evaluate and select). Maximizes creative exploration before narrowing down.

Contextual data attached and managed by the client

Name	Description
`Compare Ducks`	Interactive UI for Compare Ducks
`Duck Vote`	Interactive UI for Duck Vote
`Duck Debate`	Interactive UI for Duck Debate
`Usage Stats`	Interactive UI for Usage Stats

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/nesquikm/mcp-rubber-duck'

If you have feedback or need assistance with the MCP directory API, please join our Discord server