AI Develop Assistant
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@AI Develop Assistanthelp me design a chatbot for customer support"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
🚀 MCP AI开发助手
协助AI开发者进行智能化需求分析与架构设计的MCP工具
✨ 核心特性
智能需求澄清: 自动识别项目类型,生成针对性问题
分支感知管理: 跟踪项目目标、功能设计、技术偏好、UI设计等维度
架构自动生成: 基于完整需求生成技术架构方案
持久化存储: 自动保存分析结果,支持导出文档
Related MCP server: Doclea MCP
📁 快速配置
旧版本配置
克隆代码
git clone https://github.com/jiemobasixiangcai/ai-develop-assistant.git推荐虚拟环境
python -m venv venv source venv/bin/activate # Unix/Linux/MacOS venv\Scripts\activate # Windows安装依赖
pip install -r requirements.txt配置文件位置
Windows: %APPDATA%\Claude\claude_desktop_config.json macOS: ~/Library/Application Support/Claude/claude_desktop_config.json添加配置
{ "mcpServers": { "ai-develop-assistant": { "command": "python", "args": ["path/to/AIDevlopStudy.py"], "env": { "MCP_STORAGE_DIR": "./mcp_data" } } } }重启Claude Desktop
新版本配置
🔧 核心工具
start_new_project - 开始新项目
create_requirement_blueprint - 创建需求蓝图
requirement_clarifier - 获取需求澄清提示
save_clarification_tasks - 保存澄清任务
update_branch_status - 更新分支状态
requirement_manager - 需求文档管理器
check_architecture_prerequisites - 检查架构前置条件
get_architecture_design_prompt - 获取架构设计提示
save_generated_architecture - 保存生成的架构设计
export_final_document - 导出完整文档
view_requirements_status - 查看需求状态
配置(远程直连复制到你的工具中,将MCP_STORAGE_DIR替换为你的本地目录)
{
"mcpServers": {
"ai-develop-assistant": {
"command": "uvx",
"args": ["ai-develop-assistant@latest"],
"env": {
"MCP_STORAGE_DIR": "/path/to/your/storage"
}
}
}
}🎯 使用流程
基本步骤
需求澄清
requirement_clarifier("我要做一个在线教育平台")需求管理
requirement_manager("目标用户:学生和教师", "项目概述")查看状态
view_requirements_status()架构设计
architecture_designer("在线教育平台架构")导出文档
export_final_document()
🚀 开始使用
快速上手
配置Claude Desktop (参考上面的配置方法)
重启Claude Desktop
开始智能需求分析:
requirement_clarifier("描述你的项目想法")跟随AI的智能引导,逐步完善各个需求分支
导出完整文档:
export_final_document()
最佳实践
💬 信任AI的分支管理:让AI引导你完成所有需求分支
🎯 明确表达偏好:对技术选型、UI风格等明确表达偏好
📊 定期查看状态:使用
view_requirements_status了解进度🤖 适当授权AI:对不确定的部分可以说"用常规方案"
🎯 现在您拥有了一个真正智能的AI开发助手,它会记住每个细节,引导您完成完整的需求分析!
💬 交流群
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseBqualityDmaintenanceEnables AI-guided spec-driven development workflow that transforms ideas into implementation through structured stages: goal collection, requirements gathering in EARS format, technical design documentation, task planning, and systematic code execution.Last updated91621MIT

Doclea MCPofficial
Alicense-qualityCmaintenanceProvides persistent memory for AI coding assistants, storing and retrieving architectural decisions, patterns, and solutions across sessions using semantic search, while also offering git integration for commit messages and code expertise mapping.Last updatedMIT- Flicense-qualityDmaintenanceEnables AI development tools to maintain context across chat sessions with automatic branching, progress tracking, and TODO management for different tasks.Last updated
- Alicense-qualityDmaintenanceProvides AI-powered development assistance with continuous chain-of-thought reasoning (CoConuT), automated task planning and execution, quality validation, and persistent memory of project context and decisions.Last updated312MIT
Related MCP Connectors
AI Agent with Architectural Memory. Impact analysis (free), tests and code from the graph (pro).
Adaptive plan/build/review cycles for AI coding assistants, persisted across sessions.
Give your AI agent a persistent map of your project's structure, dependencies, and bugs.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/jiemobasixiangcai/ai-develop-assistant'
If you have feedback or need assistance with the MCP directory API, please join our Discord server