Smallest AI MCP Server

Smallest AI MCP Server

Production-grade ModelContextProtocol (MCP) server for the Waves Text-to-Speech and Voice Cloning platform.
Fast, portable, and ready for real-world AI voice workflows.

---

🚀 Overview

Smallest AI MCP Server provides a seamless bridge between the powerful Waves TTS/Voice Cloning API and any MCP-compatible LLM or agent. It is designed for speed, security, and ease of deployment.

---

✨ Features

• 🎤 List and preview voices — Instantly fetch all available voices from Waves.
• 🗣️ Synthesize speech — Convert text to high-quality WAV audio files.
• 👤 Clone voices — Create instant/professional voice clones.
• 🗂️ Manage clones — List and delete your cloned voices.

All features are implemented as MCP tools, with no placeholders or stubs.

---

⚡ Quickstart

# 1. Clone the repo
$ git clone https://github.com/Akshay-Sisodia/smallest-ai-mcp.git
$ cd smallest-ai-mcp

# 2. Install dependencies
$ pip install -r requirements.txt

# 3. Configure your API key
$ cp .env.example .env
# Edit .env and add your real WAVES_API_KEY

# 4. Start the server
$ python server.py

---

🐳 Docker Usage

# Build the Docker image
$ docker build -t smallest-ai-mcp .

# Run the container
$ docker run -p 8000:8000 \
    -e WAVES_API_KEY=your_waves_api_key \
    smallest-ai-mcp

---

🛠️ Tech Stack

• Python 3.11+
• Starlette, requests, httpx
• modelcontextprotocol/mcp-sdk

---

🏗️ Production & Deployment

• Environment: Copy .env.example to .env and add your API key. Never commit secrets to git.
• Dependencies: Install with pip install -r requirements.txt (Python 3.11+).
• Docker: Use the provided Dockerfile for containerization.
• Security: API keys are required at startup and never exposed.
• License: MIT (see LICENSE).

---

🤝 Contributing

Pull requests and issues are welcome! Please open an issue to discuss major changes.

---

👤 Maintainer

• Akshay Sisodia (GitHub)

---

📄 License

MIT

Groq MCP Client

A Streamlit application that connects to an MCP (Model Context Protocol) server and uses Groq's LLM API for chat conversations with tool execution capabilities.

Features

• Connect to any MCP server using the official MCP SDK via SSE (Server-Sent Events)
• Asynchronous communication with the MCP server
• Chat interface with streaming responses from Groq
• Tool execution through the MCP server
• Clean and user-friendly UI

Requirements

• Python 3.8+
• Groq API key
• An MCP server that supports SSE (running on HTTP)
• MCP SDK (automatically installed with requirements.txt)

Installation

1. Clone this repository
2. Install the dependencies:

pip install -r requirements.txt

Usage

1. Run the application:

streamlit run groq_mcp_client.py

2. In the Streamlit UI:
   • Enter your Groq API key in the sidebar
   • Enter the URL of your MCP server (default: http://localhost:8000)
   • Click "Connect to MCP Server"
   • Start chatting!

How it works

1. The application starts and connects to the MCP server using the official MCP SDK via SSE
2. The MCP server provides a list of available tools
3. When you send a message:
   • The message is sent to Groq's API
   • If Groq decides to use a tool, the tool call is executed through the MCP server
   • The tool results are sent back to Groq
   • Groq provides a final response

Implementation Details

• Uses the official MCP SDK for communication with MCP servers
• Connects via SSE (Server-Sent Events) for HTTP-based servers
• Implements async/await pattern for efficient server communication
• Maintains compatibility with the Streamlit UI framework

Customization

You can modify the following aspects of the application:

• Change the Groq model by modifying the model parameter in the GroqClient.generate_stream method
• Customize the UI by modifying the Streamlit components
• Add additional functionality to the MCP client

License

MIT