{"type":"mcp_client","name":"ultra-mcp","description":"**MCP client for enhanced coding tools. Boost Claude, Gemini, Cursor & more with context-aware code generation.**","category":"AI","language":"TypeScript","stars":274,"forks":9,"owner":"RealMikeChong","github_url":"https://github.com/RealMikeChong/ultra-mcp","homepage":null,"setup":"## Setup\n\nThis section outlines the steps to install, configure, and run Ultra MCP.\n\n### Prerequisites\n\n*   **Node.js:** Ensure you have Node.js installed (version 18 or higher recommended). You can download it from [nodejs.org](https://nodejs.org/).\n*   **npm:** Node Package Manager (npm) is included with Node.js. Verify it's installed by running `npm -v` in your terminal.\n\n### Installation\n\nYou can install Ultra MCP globally using npm or run it directly with npx.\n\n**Option 1: Global Installation (Recommended)**\n\n```bash\nnpm install -g ultra-mcp\n```\n\nThis installs Ultra MCP as a global command, making it accessible from any directory in your terminal.\n\n**Option 2: Using npx (No Installation)**\n\n```bash\nnpx -y ultra-mcp config\n```\n\nThis runs Ultra MCP directly without installing it globally. The `-y` flag automatically confirms any prompts during installation.\n\n### Configuration\n\nAfter installation, you need to configure Ultra MCP with your API keys for the AI providers you want to use (OpenAI, Gemini, Azure OpenAI, Grok).\n\nRun the interactive configuration command:\n\n```bash\nnpx -y ultra-mcp config\n```\n\nThis command will:\n\n1.  Show the current configuration status.\n2.  Present a provider-first menu to select which AI provider to configure.\n3.  Guide you through setting API keys, base URLs (if required), and preferred models.\n4.  Store the configuration securely on your system.\n5.  Auto-load settings when the server starts.\n\n**OpenAI-Compatible Support:** The configuration also supports OpenAI-compatible APIs like Ollama (local) or OpenRouter (400+ models).\n\n### Running the Server\n\nOnce configured, start the Ultra MCP server:\n\n```bash\nnpx -y ultra-mcp\n```\n\nThis will start the MCP server, allowing Claude Code and Cursor to access the configured AI models.\n\n**Alternatively, after building locally:**\n\n```bash\nnpm run build\nnode dist/cli.js\n```\n\n### Environment Variables\n\nYou can also set API keys and base URLs using environment variables. This is useful for automated deployments or when you prefer not to store API keys in a configuration file.\n\n*   `OPENAI_API_KEY` / `OPENAI_BASE_URL`\n*   `GOOGLE_API_KEY` / `GOOGLE_BASE_URL`\n*   `AZURE_API_KEY` / `AZURE_BASE_URL` (base URL required for Azure)\n*   `XAI_API_KEY` / `XAI_BASE_URL`\n\n**Note:** Configuration file settings take precedence over environment variables.\n\n### Vector Embeddings Configuration\n\nUltra MCP supports vector embeddings for semantic code search. By default, it uses `text-embedding-3-small` for cost efficiency. You can customize the embedding models in your configuration file (see the original README for details).","tools":"## Available Tools\n\n- 🤖 **Multi-Model Support**: Integrates OpenAI (O3), Google Gemini (2.5 Pro), Azure OpenAI, and xAI Grok models.\n- 🔌 **MCP Protocol**: Provides a standard Model Context Protocol interface for seamless integration with tools like Claude Code and Cursor.\n- 🧠 **Deep Reasoning Tools**: Accesses powerful AI models (like O3) for complex problem-solving.\n- 🔍 **Investigation & Research**: Offers built-in tools for thorough investigation and research tasks.\n- 🌐 **Google Search Integration**: Leverages Gemini 2.5 Pro with real-time web search capabilities.\n- ⚡ **Real-time Streaming**: Delivers live model responses via Vercel AI SDK.\n- 🔧 **Zero Config**: Enables interactive setup with smart defaults for quick configuration.\n- 🔑 **Secure Configuration**: Stores API keys locally using the `conf` library for enhanced security.\n- 🧪 **TypeScript**: Ensures full type safety and a modern development experience.\n\n**MCP Tools (Accessible through Claude Code and Cursor):**\n\n### 🧠 Deep Reasoning (`deep-reasoning`)\n\nLeverages advanced AI models for complex problem-solving and analysis.\n\n- **Default**: O3 for OpenAI/Azure, Gemini 2.5 Pro with Google Search, Grok-4 for xAI\n- **Use Cases**: Complex algorithms, architectural decisions, deep analysis\n\n```javascript\n// In Claude Code or Cursor with MCP\nawait use_mcp_tool('ultra-mcp', 'deep-reasoning', {\n  provider: 'openai',\n  prompt: 'Design a distributed caching system for microservices',\n  reasoningEffort: 'high',\n});\n```\n\n### 🔍 Investigate (`investigate`)\n\nThoroughly investigates topics with configurable depth levels.\n\n- **Depth Levels**: shallow, medium, deep\n- **Google Search**: Enabled by default for Gemini\n- **Use Cases**: Research topics, explore concepts, gather insights\n\n### 📚 Research (`research`)\n\nConducts comprehensive research with multiple output formats.\n\n- **Output Formats**: summary, detailed, academic\n- **Use Cases**: Literature reviews, technology comparisons, documentation\n\n### 📋 List Models (`list-ai-models`)\n\nViews all available AI models and their configuration status.","faq":null,"created_at":"2025-06-28T15:41:40+00:00","updated_at":"2025-08-08T10:00:27+00:00","source_url":"https://model-context-protocol.com/clients/ultra-mcp","related_articles":[]}