Intelligent Architecture Recommendation Engine
DevOpsby deeppath-ai
根据 QPS、并发用户、数据库类型和 AI 模型规模,生成定制化系统架构建议,并给出资源配置、中间件、部署策略与可导出图表。
什么是 Intelligent Architecture Recommendation Engine?
根据 QPS、并发用户、数据库类型和 AI 模型规模,生成定制化系统架构建议,并给出资源配置、中间件、部署策略与可导出图表。
README
mcp-system-infra
</div>🚀 Intelligent Architecture Recommendation Engine: Tailored for Your System
In today's rapidly evolving digital landscape, how can you quickly and efficiently build a scalable and reliable technical infrastructure? The Intelligent Architecture Recommendation Engine is here to solve that challenge.
Based on key parameters—QPS (queries per second), concurrent users, daily active users, business type, database choice, and AI model size—this tool automatically generates:
- 💡 Optimal server resource allocation
- 🧩 Required middleware module combinations
- 🏗️ Recommended overall system architecture
- ☁️ Suggested cloud providers and deployment strategies
- 📊 One-click export of Markdown report + architecture diagram
✨ Key Benefits
✅ Fully Parameter-Driven, Business-Oriented
Simply provide the following parameters:
--qps: Peak request throughput--concurrentUsers: Number of concurrent connections--uad: Daily Active Users (UAD)--type: Business type (web/ai)--db: Database type (relational/nosql/analytics)--model: AI model size (small/medium/large)
The system will automatically assess and recommend:
- CPU / Memory / Network configuration
- Redis cache capacity and eviction strategy
- Message queue type and concurrency handling
- Whether to adopt a microservices architecture
- Whether to enable distributed architecture and GPU inference clusters
🗺️ Architecture Recommendation Diagram
The system automatically generates a Mermaid diagram to clearly represent component relationships:
flowchart TD
User[User Request] --> Nginx[Nginx Load Balancer]
Nginx --> Service[Main Business Service Node]
Service --> DB[Database]
Service --> Redis[Redis Cache]
Service --> MQ[Message Queue]
Service --> GPU[AI Inference GPU Node]
MQ --> Consumer[Asynchronous Consumer]
<div align="center">▶️ Quick Start</div>
CLI
npx -y mcp-system-infra
MCP Server Configuration
{
"mcpServers": {
"mcp-system-infra": {
"command": "npx",
"args": [
"-y",
"mcp-system-infra"
]
}
}
}
MCP Example:
Please help design a web-based system architecture report with the following specifications:
- QPS (Queries Per Second): 100
- Concurrent Users: 50
- Daily Active Users: 300
- Database Type: Relational
- Model Size: Medium
<div align="center">💭 Murmurs</div>
This project is for educational and internal use only. Contributions and feedback are welcome.
For feature customization, web deployment, or enterprise integration, please contact the project maintainer.
Business Contact Email: deeppathai@outlook.com
🧠 MCP Access Addresses
-
🌐 ModelScope MCP Address
For testing and integratingmcp-system-infradirectly within the ModelScope platform. -
🛠️ Smithery.ai MCP Address
For visual configuration and invocation of themcp-system-infraservice via Smithery.
常见问题
Intelligent Architecture Recommendation Engine 是什么?
根据 QPS、并发用户、数据库类型和 AI 模型规模,生成定制化系统架构建议,并给出资源配置、中间件、部署策略与可导出图表。
相关 Skills
可观测性设计
by alirezarezvani
面向生产系统规划可落地的可观测性体系,串起指标、日志、链路追踪与 SLI/SLO、错误预算、告警和仪表盘设计,适合搭建监控平台与优化故障响应。
✎ 把监控、日志、链路追踪串起来,帮助团队从设计阶段构建可观测性,排障更快、系统演进更稳。
资深开发运维
by alirezarezvani
覆盖 CI/CD 流水线生成、Terraform 基建脚手架和自动化部署,适合在 AWS、GCP、Azure 上搭建云原生发布流程,管理 Docker/Kubernetes 基础设施并持续优化交付。
✎ 把CI/CD、基础设施即代码、容器与监控串成一条交付链,尤其适合AWS/GCP/Azure多云团队高效落地。
环境密钥管理
by alirezarezvani
统一梳理dev/staging/prod的.env和密钥流程,自动生成.env.example、校验必填变量、扫描Git历史泄漏,并联动Vault、AWS SSM、1Password、Doppler完成轮换。
✎ 统一管理环境变量、密钥与配置,减少泄露和部署混乱,安全治理与团队协作一起做好,DevOps 场景很省心。
相关 MCP Server
kubefwd
编辑精选by txn2
kubefwd 是让 AI 帮你批量转发 Kubernetes 服务到本地的开发神器。
✎ 微服务开发者最头疼的本地调试问题,它一键搞定——自动分配 IP 避免端口冲突,还能用自然语言查询状态。但依赖 AI 工作流,纯命令行爱好者可能觉得不够直接。
Cloudflare
编辑精选by Cloudflare
Cloudflare MCP Server 是让你用自然语言管理 Workers、KV 和 R2 等云资源的工具。
✎ 这个工具解决了开发者频繁切换控制台和文档的痛点,特别适合那些在 Cloudflare 上部署无服务器应用、需要快速调试或管理配置的团队。不过,由于它依赖多个子服务器,初次设置可能有点繁琐,建议先从 Workers Bindings 这类核心功能入手。
Terraform
编辑精选by hashicorp
Terraform MCP Server 是让 AI 助手直接操作 Terraform Registry 和 HCP Terraform 的桥梁。
✎ 如果你经常在 Terraform 里翻文档找模块配置,这个服务器能省不少时间——直接问 Claude 就能生成准确的代码片段。最适合管理多云基础设施的团队,但注意它目前只适合本地使用,别在生产环境里暴露 HTTP 端点。