# multimodal-mcp-client

> MCP Client

This repository offers a voice-controlled AI interface using Google Gemini and Anthropic MCP, enabling natural speech and multimodal inputs for interacting with AI systems. It supports both custom and Systemprompt MCP servers.

## Overview

- **Category:** AI
- **Language:** TypeScript
- **Stars:** 211
- **Forks:** 21
- **Owner:** Ejb503
- **GitHub:** https://github.com/Ejb503/multimodal-mcp-client
- **Homepage:** https://systemprompt.io
- **Created:** 2025-01-08T07:50:46+00:00
- **Updated:** 2025-03-27T16:47:22+00:00
- **Source:** https://model-context-protocol.com/clients/voice-controlled-ai-agentic-workflows-client

## Setup

## Setup

1. **Clone the repository**

   ```bash
   git clone https://github.com/Ejb503/multimodal-mcp-client.git
   cd multimodal-mcp-client
   ```

2. **Install dependencies**

   ```bash
   npm install
   cd proxy
   npm install
   ```

3. **Configure the application**

   ```bash
   # Navigate to config directory
   cd config

   # Create local configuration files
   cp mcp.config.example.json mcp.config.custom.json
   ```

   Required API Keys:

   - [Google AI Studio](https://ai.google.dev/gemini-api/docs) - Gemini API key
   - [systemprompt.io/console](https://systemprompt.io/console) - Systemprompt API key

   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**
   ```bash
   npm run dev
   ```
   Access the development server at `http://localhost:5173`

## Tools

## Available Tools

1.  **Multimodal AI** (Understand and process text, voice, and visual inputs naturally)
2.  **MCP (Model Control Protocol)** (Execute complex AI workflows with a robust tooling system)
3.  **Voice-First Design** (Control everything through natural speech, making AI interaction more intuitive)
4.  **Natural Voice Control** (Speak naturally to control AI workflows and execute commands)
5.  **Multimodal Understanding** (Process text, voice, and visual inputs simultaneously)
6.  **Real-time Voice Synthesis** (Get instant audio responses from your AI interactions)
7.  **Extensible Tool System** (Add custom tools and workflows through MCP)
8.  **Workflow Automation** (Chain multiple AI operations with voice commands)
9.  **State Management** (Robust handling of complex, multi-step AI interactions)
10. **Modern Tech Stack** (Built with Vite, React, TypeScript, and NextUI)
11. **Type Safety** (Full TypeScript support with comprehensive type definitions)
12. **Hot Module Replacement** (Fast development with instant feedback)
13. **Comprehensive Testing** (Built-in testing infrastructure with high coverage)