TS

multimodal-mcp-client

by Ejb503/multimodal-mcp-client

0 views

A Multi-modal MCP client for voice powered agentic workflows

automationnodejstypescriptAPI Integration

Systemprompt Multimodal MCP Client

Discord Twitter Follow Linkedin

Website โ€ข Documentation โ€ข Blog โ€ข Get API Key

A modern voice-controlled AI interface powered by Google Gemini and Anthropic MCP (Model Control Protocol). Transform how you interact with AI through natural speech and multimodal inputs.

โš ๏ธ Important Note: This open source project is currently in development and in early access. It is not currently compatible with Safari but has been tested on Chrome with Linux, Windows, and MacOS. If you have any problems, please let us know on Discord or GitHub.

If you find this project useful, please consider:

  • โญ Starring it on GitHub
  • ๐Ÿ”„ Sharing it with others
  • ๐Ÿ’ฌ Joining our Discord community

๐ŸŒŸ Overview

A modern Vite + TypeScript application that enables voice-controlled AI workflows through MCP (Model Control Protocol). This project revolutionizes how you interact with AI systems by combining Google Gemini's multimodal capabilities with MCP's extensible tooling system.

The Client supports both custom (user provided and configured) and Systemprompt MCP servers. Systemprompt MCP servers can be installed through the UX with a Systemprompt API key (free).

Custom MCP servers are not pre-configured and require a custom configuration file.

Create a local file mcp.config.custom.json in the config directory and add your MCP server configuration.

{
  "mcpServers": {
    "my-custom-server": {
      "id": "my-custom-server",
      "env": {
        "xxx": "xxx"
      },
      "command": "node",
      "args": [
        "/my-custom-server/build/index.js"
      ]
    }
  }
}

๐ŸŽฏ Why Systemprompt MCP?

Transform your AI interactions with a powerful voice-first interface that combines:

FeatureDescription
๐Ÿ—ฃ๏ธ Multimodal AIUnderstand and process text, voice, and visual inputs naturally
๐Ÿ› ๏ธ MCP (Model Control Protocol)Execute complex AI workflows with a robust tooling system
๐ŸŽ™๏ธ Voice-First DesignControl everything through natural speech, making AI interaction more intuitive

Perfect for: Developers building voice-controlled AI applications and looking for innovative ways to use multimodal AI.

โœจ Core Features

๐ŸŽ™๏ธ Voice & Multimodal Intelligence

  • Natural Voice Control: Speak naturally to control AI workflows and execute commands
  • Multimodal Understanding: Process text, voice, and visual inputs simultaneously
  • Real-time Voice Synthesis: Get instant audio responses from your AI interactions

๐Ÿ”„ AI Workflow Orchestration

  • Extensible Tool System: Add custom tools and workflows through MCP
  • Workflow Automation: Chain multiple AI operations with voice commands
  • State Management: Robust handling of complex, multi-step AI interactions

๐Ÿ’ป Developer Experience

  • Modern Tech Stack: Built with Vite, React, TypeScript, and NextUI
  • Type Safety: Full TypeScript support with comprehensive type definitions
  • Hot Module Replacement: Fast development with instant feedback
  • Comprehensive Testing: Built-in testing infrastructure with high coverage

๐Ÿš€ Getting Started

Prerequisites

  • Node.js 16.x or higher
  • npm 7.x or higher
  • A modern browser with Web Speech API support

Quick Start

  1. Clone the repository

    git clone https://github.com/Ejb503/multimodal-mcp-client.git
    cd multimodal-mcp-client
    
  2. Install dependencies

    npm install
    cd proxy
    npm install
    
  3. Configure the application

    # Navigate to config directory
    cd config
    
    # Create local configuration files
    cp mcp.config.example.json mcp.config.custom.json
    

    Required API Keys:

    Add keys to .env (see .env.example for reference). note that the VITE_ prefix is required to share the keys with the MCP server and client.

  4. Start development server

    npm run dev
    

    Access the development server at http://localhost:5173

๐Ÿค Support & Community

ResourceLink
๐Ÿ’ฌ DiscordJoin our community
๐Ÿ› IssuesGitHub Issues
๐Ÿ“š DocsDocumentation

๐Ÿ“„ License

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

๐Ÿ”ฎ Future Development

We're actively working on expanding the capabilities of Systemprompt MCP Client with exciting new features and extensions. Stay tuned for updates!

Install

{
  "mcpServers": {
    "multimodal-mcp-client": {
      "command": "node",
      "args": [
        "/my-custom-server/build/index.js"
      ]
    }
  }
}
For more configuration details, refer to the content on the left

Related

Related projects feature coming soon

Will recommend related projects based on sub-categories