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!
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.