Skip to content
Conduit

mcp server

Ultimate-MCP

An MCP to be used with OpenRouter API key to use the best models for debugging and content creation.

RaiAnsar/Ultimate-MCPcommunitylistedunreviewed
Use tool

Set up

Runs on your computer. Pick your agent and operating system.

Before you start

  • Node.js 20 or newer
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "ultimate-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "ultimate-mcp-server"
      ]
    }
  }
}

same format Cursor, GitHub Copilot CLI, Junie, JetBrains AI Assistant, Augment (Auggie CLI), Factory Droid, Kiro, Devin CLI +12

Values in angle brackets are placeholders. Restart Claude Desktop after editing its config.Claude Desktop docs

README

synced Oct 27, 2026

Ultimate MCP Server

🎯 Quick Installation

✨ Features

🤖 AI Models (50+)

  • OpenAI: GPT-4o, GPT-4o-mini, o1-preview
  • Anthropic: Claude 3 Opus, Sonnet, Haiku
  • Google: Gemini 2.5 Pro/Flash
  • xAI: Grok-2, Grok-3, Grok-4 (Beta)
  • DeepSeek: V3, R1, Coder V2
  • Meta: Llama 3.3 70B/405B
  • Mistral: Large 2411, Codestral
  • And many more...

🛠️ Tool Categories (81 Tools)

  • Code Analysis: Error debugging, optimization
  • Code Generation: Multi-language support
  • Large Codebase: 1M+ token analysis
  • RAG System: Vector search, embeddings
  • Browser Automation: Web scraping, testing
  • UI/UX Analysis: Design system extraction
  • Cognitive Memory: Knowledge graphs
  • Content Management: Documentation

📦 Installation Guides

Claude Desktop

Method 1: Using Claude's Official Tool

npx @claude/create-mcp-server
# Select "ultimate-mcp-server" from the list

Method 2: Manual Configuration

  1. Open Claude Desktop settings
  2. Navigate to Developer → Model Context Protocol
  3. Click "Add Server" and enter:
    • Name: ultimate
    • Command: npx
    • Arguments: ultimate-mcp-server

Method 3: Edit Configuration File

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "ultimate": {
      "command": "npx",
      "args": ["ultimate-mcp-server"],
      "env": {
        "OPENROUTER_API_KEY": "your-key-here"
      }
    }
  }
}

Claude Code

Quick Install (Recommended)

claude mcp add ultimate npx ultimate-mcp-server

With API Keys

claude mcp add ultimate npx ultimate-mcp-server \
  -e OPENROUTER_API_KEY=your-key \
  -e ANTHROPIC_API_KEY=your-key \
  -e GOOGLE_API_KEY=your-key

Local Development

# Clone and build
git clone https://github.com/RaiAnsar/ultimate-mcp-server.git
cd ultimate-mcp-server
npm install && npm run build

# Add local version
claude mcp add ultimate node ./dist/index.js

Verify Installation

claude mcp list
# Should show: ultimate: npx ultimate-mcp-server - ✓ Connected

Cursor

  1. Open Cursor Settings (Cmd/Ctrl + ,)
  2. Search for "MCP" or navigate to Features → MCP
  3. Click "Add MCP Server"
  4. Configure:
{
  "name": "ultimate",
  "command": "npx",
  "args": ["ultimate-mcp-server"],
  "env": {
    "OPENROUTER_API_KEY": "your-key-here"
  }
}
  1. Restart Cursor to activate

Alternative: Direct Config Edit

Edit ~/.cursor/config/settings.json:

{
  "mcp": {
    "servers": {
      "ultimate": {
        "command": "npx",
        "args": ["ultimate-mcp-server"],
        "env": {
          "OPENROUTER_API_KEY": "your-key"
        }
      }
    }
  }
}

VS Code (Continue Extension)

  1. Install Continue extension from VS Code marketplace
  2. Open Continue settings (Cmd/Ctrl + Shift + P → "Continue: Open Settings")
  3. Add MCP configuration:
{
  "models": [...],
  "mcpServers": {
    "ultimate": {
      "command": "npx",
      "args": ["ultimate-mcp-server"],
      "env": {
        "OPENROUTER_API_KEY": "your-key"
      }
    }
  }
}
  1. Reload VS Code window

Windsurf

  1. Open Windsurf Settings
  2. Navigate to AI → MCP Servers
  3. Click "Add Server"
  4. Enter configuration:
name: ultimate
command: npx
args:
  - ultimate-mcp-server
env:
  OPENROUTER_API_KEY: your-key
  1. Save and restart Windsurf

Cline

Add to ~/.cline/config.json:

{
  "mcpServers": {
    "ultimate": {
      "command": "npx",
      "args": ["ultimate-mcp-server"],
      "env": {
        "OPENROUTER_API_KEY": "your-key"
      }
    }
  }
}

Google AI Studio

  1. Open Google AI Studio
  2. Go to Settings → Extensions
  3. Enable MCP Support
  4. Add server configuration:
{
  "ultimate": {
    "command": "npx",
    "args": ["ultimate-mcp-server"],
    "transport": "stdio"
  }
}

🔑 API Configuration

Required API Keys (at least one)

ProviderEnvironment VariableGet API KeyModels
OpenRouterOPENROUTER_API_KEYGet KeyAll 50+ models
AnthropicANTHROPIC_API_KEYGet KeyClaude models
OpenAIOPENAI_API_KEYGet KeyGPT models
GoogleGOOGLE_API_KEYGet KeyGemini models
PerplexityPERPLEXITY_API_KEYGet KeyOnline search

Setting API Keys

Method 1: Environment Variables

export OPENROUTER_API_KEY="sk-or-..."
export ANTHROPIC_API_KEY="sk-ant-..."

Method 2: .env File

Create .env in your project:

OPENROUTER_API_KEY=sk-or-...
ANTHROPIC_API_KEY=sk-ant-...
GOOGLE_API_KEY=...

Method 3: MCP Configuration

Add to your MCP client config:

{
  "env": {
    "OPENROUTER_API_KEY": "your-key",
    "ANTHROPIC_API_KEY": "your-key"
  }
}

🚀 Usage Examples

Basic Commands

# Start server (stdio mode)
npx ultimate-mcp-server

# With specific transport
ENABLE_SSE=true npx ultimate-mcp-server

# With multiple transports
ENABLE_HTTP=true ENABLE_WEBSOCKET=true npx ultimate-mcp-server

Tool Examples

Ask AI

// In your MCP client
await callTool('ask', {
  prompt: 'Explain async/await in JavaScript',
  model: 'openai/gpt-4o'
});

Analyze Error

await callTool('analyze_error', {
  error: 'TypeError: Cannot read property "x" of undefined',
  language: 'javascript'
});

Generate Code

await callTool('generate_code', {
  description: 'Binary search algorithm',
  language: 'python',
  includeTests: true
});

Analyze Large Codebase

await callTool('analyze_large_codebase', {
  rootDir: './src',
  query: 'Find all API endpoints',
  pattern: '.*\\.(ts|js)$'
});

📊 Tool Categories

  • ask - Query specific AI models
  • orchestrate - Multi-model orchestration
  • generate_code - AI code generation
  • explain_code - Code explanation
  • suggest_optimizations - Performance optimization
  • debugging_session - Interactive debugging
  • analyze_error - Error analysis
  • analyze_codebase - Codebase analysis
  • find_in_codebase - Pattern search
  • get_metrics - Performance metrics
  • analyze_large_codebase - Analyze with 1M+ tokens
  • generate_directory_tree - Visual directory structure
  • collect_code_context - Context collection
  • analyze_project_structure - Architecture analysis
  • find_codebase_patterns - Pattern detection
  • generate_project_docs - Auto documentation
  • estimate_analysis_cost - Cost estimation
  • rag_ingest_document - Document ingestion
  • rag_search - Semantic search
  • rag_query - Q&A with sources
  • build_knowledge_graph - Graph construction
  • cognitive_search - Memory search
  • build_memory_context - Context building
  • get_related_memories - Related concepts
  • export_knowledge_graph - Graph export
  • analyze_ui_design - UI/UX analysis
  • extract_design_system - Design tokens
  • check_ui_accessibility - WCAG compliance
  • compare_ui_designs - A/B comparison
  • suggest_ui_improvements - UX suggestions
  • analyze_ui_components - Component audit
  • create_ui_style_guide - Style documentation
  • analyze_user_flow - Journey mapping
  • browser_navigate - Web navigation
  • browser_screenshot - Page capture
  • universal_search - Multi-provider search
  • search_files - File search
  • search_content - Content grep
  • search_processes - Process search
  • search_everything - Unified search

🏗️ Architecture

graph TB
    A[MCP Client] -->|stdio/sse/http/ws| B[Transport Layer]
    B --> C[Ultimate MCP Server]
    C --> D[Tool Registry - 81 Tools]
    C --> E[AI Orchestrator]
    C --> F[Resource Manager]
    
    E --> G[OpenRouter - 50+ Models]
    E --> H[Direct Providers]
    
    D --> I[Code Intelligence]
    D --> J[Browser Automation]
    D --> K[RAG System]
    D --> L[UI Analysis]

🔧 Development

# Clone repository
git clone https://github.com/RaiAnsar/ultimate-mcp-server.git
cd ultimate-mcp-server

# Install dependencies
npm install

# Build project
npm run build

# Run tests
npm test

# Development mode
npm run dev

Project Structure

ultimate-mcp-server/
├── src/
│   ├── core/           # Core MCP functionality
│   ├── tools/          # All 81 tools
│   ├── providers/      # AI providers
│   ├── transports/     # Transport layers
│   └── utils/          # Utilities
├── dist/               # Compiled output
└── package.json

🤝 Contributing

Contributions are welcome! Please read our Contributing Guide for details.

  1. Fork the repository
  2. Create your feature branch (git checkout -b feature/AmazingFeature)
  3. Commit your changes (git commit -m 'Add some AmazingFeature')
  4. Push to the branch (git push origin feature/AmazingFeature)
  5. Open a Pull Request

📝 License

This project is licensed under the MIT License - see the LICENSE file for details.

🆘 Support

⭐ Star History

Star History Chart

↑↓ navigate openesc close