general MCP Server
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!
Discovered via unknown and last synced 3mo ago.
1. Install the package
npx mcp-rubber-duck
2. Add to claude_desktop_config.json
{
"mcpServers": {
"mcp-rubber-duck": {
"command": "npx",
"args": [
"mcp-rubber-duck"
]
}
}
}Config file location: ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) / %APPDATA%\Claude\claude_desktop_config.json (Windows)
Default temperature (e.g., `0.7`)
List configured providers and health status
Structured multi-round debate between ducks
Set to `true` for MCP server mode
Ask the same question to multiple providers simultaneously
Pending MCP tool approval requests
Description
OpenAI API key
Google Gemini API key
Groq API key
Default provider (e.g., `openai`)
`debug`, `info`, `warn`, `error`
Enable MCP Bridge (ducks access external MCP servers)
Get responses from all configured ducks
Approve or deny a duck's MCP tool request
Description
Usage statistics and estimated costs
Purpose
Divergent exploration then convergence
Ask a single question to a specific LLM provider
Multi-duck voting with reasoning and confidence
Multi-angle analysis with assigned lenses
Conversation with context maintained across messages
Have one duck evaluate and rank others' responses
Surface hidden assumptions in plans
[docs/guardrails.md](./docs/guardrails.md)
Clear all conversation history
List available models for providers
Iteratively refine a response between two ducks
Hunt for overlooked risks and gaps
MCP Bridge status and connected servers
Security/risk analysis from multiple angles
Structured option comparison
[docs/roadmap.md](./docs/roadmap.md)
Problem reframing at different levels
Design review across concerns
Link
[docs/architecture.md](./docs/architecture.md)