Simple Design MCP Orchestrator
Orchestrates app design workflows for Claude Code local execution, enabling creation, updating, and component addition without rate limits.
README
Simple Design MCP Orchestrator v3.0
Orchestrates app design workflows for Claude Code local execution - no more rate limits! 🎯
What's New in v3.0 - The Orchestrator Architecture
The Problem We Solved
- v2.0 Issue: MCP server did all the work, hitting rate limits (100 req/min)
- v3.0 Solution: MCP returns workflows, Claude Code executes locally using YOUR tokens
How It Works Now
User → Commands.com → MCP Orchestrator → Workflow Instructions → Claude Code (local execution) → Success!
Key Benefits
- 🚀 No Rate Limits - Uses your Claude Code tokens, not the server's
- ⚡ Faster Execution - No network roundtrips for AI calls
- 🔍 Full Transparency - See exactly what's happening
- 🛡️ Better Privacy - Your data stays on your machine
- 📈 Infinitely Scalable - Server just returns instructions
Available Orchestration Tools
🎼 simple_design_orchestrate
Get a complete workflow for designing apps - returns instructions for Claude Code to execute locally.
Parameters:
task: The design task (create_app,update_design,add_component)input: Task-specific parameters
Example Response:
{
"workflowId": "create_app_1234567890",
"workflow": {
"name": "Create App Workflow",
"steps": [/* step-by-step instructions */]
},
"agents": {/* agent templates */},
"components": {/* component specs */},
"estimatedTokens": 4800
}
🤖 simple_design_get_agent
Get specific agent templates for local execution.
Parameters:
agentName: Name of the agent (e.g., "DesignBrief", "UXFlow")action: Optional specific action
🧩 simple_design_get_component
Get component specifications for UI building.
Parameters:
componentName: Component to get specs forappType: Optional app type for context
How Commands Work
Creating an App
You type: /design-app "recipe sharing app"
What happens:
- MCP orchestrator analyzes your request
- Returns a workflow with:
- Design Brief agent template
- UX Flow generation instructions
- UI component specifications
- File structure guidelines
- Claude Code executes each step locally
- HTML/CSS files created on your machine
- No rate limits!
Updating a Design
You type: /update-design "make the header blue"
What happens:
- Orchestrator returns change analysis workflow
- Claude Code analyzes the change locally
- Updates files using your resources
- Instant results, no server load
Architecture Overview
Core Components
- WorkflowOrchestrator - Main orchestration engine
- AgentTemplates - Lightweight agent instructions
- ComponentSpecs - UI component specifications
- WorkflowDefinitions - Complete workflow structures
Agent Templates
DesignBrief- Analyzes app requirementsUXFlow- Creates screen structureUIGenerator- Selects UI componentsFileCreator- Generates file structureChangeAnalyzer- Understands update requestsComponentIntegrator- Adds new components
Component Library
- Navigation: navbar, sidebar
- Layout: hero, grid, container
- Content: cards, galleries, testimonials
- Forms: search, inputs, buttons
- Data: charts, stats, tables
- App-specific: recipe cards, workout cards, etc.
Installation & Setup
- Deploy to Railway (or your preferred platform)
- Import to Commands.com
- Use with Claude Code
No local installation needed - it's all orchestrated!
For Developers
Testing Locally
npm install
npm test # Run orchestrator tests
Example Integration
// Get workflow from orchestrator
const workflow = await mcp.call('simple_design_orchestrate', {
task: 'create_app',
input: { description: 'fitness app' }
});
// Execute locally in Claude Code
for (const step of workflow.steps) {
await executeStep(step, workflow.agents[step.agent]);
}
Migration from v2.0
See MIGRATION.md for upgrade instructions.
Support
- Issues: GitHub Issues
- Docs: See
/examplesfolder - Version: 3.0.0
Built with ❤️ to solve rate limiting and empower local execution!
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。