MCP Rubber Duck
未认领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!
01 / 选择客户端
03 / 添加配置
claude mcp add --transport stdio 'mcp-rubber-duck' -- 'npx' '-y' 'mcp-rubber-duck'04 / 在客户端中确认
打开客户端的 MCP 设置，确认服务器已连接并列出工具。复制配置不代表连接成功。
更多AI & ML服务器
浏览完整目录安全概况
已认领和已认证的服务器每周接受一次静态扫描，显示代码能触及的范围（外部服务、环境变量、shell 命令、代理配置目录）以及带有已知公告的依赖。认领此列表即可获得。 安全概况的工作原理
15 个工具中显示 15 个
文档中列出的工具 (15)
内容来自项目文档。服务器握手不会验证每个工具的说明或行为。
approve_mcp_request
Approve or deny a duck's MCP tool request
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
compare_ducks
Ask the same question to multiple providers simultaneously
duck_council
Get responses from all configured ducks
duck_debate
Structured multi-round debate between ducks
duck_iterate
Iteratively refine a response between two ducks
duck_judge
Have one duck evaluate and rank others' responses
duck_vote
Multi-duck voting with reasoning and confidence
get_pending_approvals
Pending MCP tool approval requests
get_usage_stats
Usage statistics and estimated costs
list_ducks
List configured providers and health status
list_models
List available models for providers
mcp_status
MCP Bridge status and connected servers