一套全面的模型上下文协议（MCP）工具模式和配方合集。本手册展示了各种MCP设计模式，您可以作为构建模块，用于自有的AI驱动应用。

🧑 🍳 可用配方（图案）

本食谱展示了关键的MCP工具模式：

🎯 提示暴露模式

• code_reviewer_prompt - 即用的全面代码审查提示
• react_prompt_generator - 动态反应（Reason + Act）模式提示生成
• 用例：将MCP转换为即时存储库服务

🤔 澄清问题模式

• smart_recipe_generator - 前瞻性信息收集，提出智能问题
• 用例：通过提出针对性的后续问题，优雅地处理不完整的用户输入

🔄 多步骤工具模式

• step1_initialize_workflow → step2_execute_workflow - 顺序工具依赖关系
• 用例：需要状态管理和有序执行的复杂工作流

🌐 客户端工具编排模式

• sequential_web_search - 桥接外部工具（如web_search）与MCP处理

MCP Tools Cookbook

A comprehensive collection of Model Context Protocol (MCP) tool patterns and recipes. This cookbook demonstrates various MCP design patterns that you can use as building blocks for your own AI-powered applications.

🧑‍🍳 Available Recipes (Patterns)

This cookbook demonstrates essential MCP tool patterns:

🎯 Prompt Exposure Pattern

• code_reviewer_prompt - Ready-to-use comprehensive code review prompts
• react_prompt_generator - Dynamic ReAct (Reason + Act) pattern prompt generation
• Use case: Transform MCP into a prompt repository service

🤔 Clarification Questions Pattern

• smart_recipe_generator - Progressive information gathering with intelligent questions
• Use case: Handle incomplete user input gracefully by asking targeted follow-up questions

🔄 Multi-Step Tool Pattern

• step1_initialize_workflow → step2_execute_workflow - Sequential tool dependencies
• Use case: Complex workflows requiring state management and ordered execution

🌐 Client Tool Orchestration Pattern

• sequential_web_search - Bridges external tools (like web_search) with MCP processing
• Use case: Extend and orchestrate native client tools from the server side

🎲 Response-Driven Navigation Pattern

• tool_with_follow_up - Tools that suggest next actions through embedded commands
• quantum_mood_analyzer, rubber_duck_debugger, coffee_brew_oracle - Fun example tools
• Use case: Guide conversation flow through tool response content

📸 Patterns in Action

See these MCP tool patterns demonstrated in real AI conversations:

🎯 Prompt Exposure Pattern

The code_reviewer_prompt tool exposing a comprehensive, ready-to-use code review template

🤔 Clarification Questions Pattern

The smart_recipe_generator tool progressively gathering information through targeted questions

🌐 Client Tool Orchestration Pattern

The sequential_web_search tool orchestrating multiple web searches and processing results

🎲 Response-Driven Navigation Pattern

The tool_with_follow_up tool suggesting next actions, leading to rubber_duck_debugger execution

🚀 Quick Start

Setup Your Kitchen (Environment)

# Create virtual environment
python3 -m venv venv

# Activate virtual environment
source venv/bin/activate

# Install dependencies
pip install -r requirements.txt

Or use the convenient activation script:

source activate.sh

Using with AI Applications

Connect this cookbook to LLM applications that support MCP: