FastAPI SSE MCP Random

A FastAPI server that implements the Model Context Protocol (MCP) using Server-Sent Events (SSE) for streaming communication. This project provides various utility tools including random number generation, image generation using Azure OpenAI DALL-E, and AI podcast generation.

Features

• Server-Sent Events (SSE) for real-time streaming communication

• Model Context Protocol (MCP) implementation for structured tool use

• Multiple utility tools:

  • Echo tool and resources

  • Random number generator

  • Image generation via Azure OpenAI DALL-E 3

  • AI podcast generation

  • "Think tool" for reflective responses

Related MCP server: AI Agent MCP Server

Prerequisites

• Python 3.10+

• Azure OpenAI API access (for image generation)

Installation

1. Clone the repository:

git clone <repository-url>
cd fastapi_sse_mcp_random

2. Install the dependencies:

pip install -r requirements.txt

Or using uv:

uv pip install -e .

Usage

Starting the server

Run the server with:

python main.py

The server will start at http://0.0.0.0:8000

Available Endpoints

• GET /: Health check endpoint

• GET /sse/: SSE connection endpoint

• POST /messages/: Endpoint for client messages

Available Tools

Echo Tool

{
  "name": "echo_tool",
  "parameters": {
    "message": "Hello, world!"
  }
}

Random Number Generator

{
  "name": "random_number",
  "parameters": {
    "min_value": 1,
    "max_value": 100
  }
}

Image Generation

{
  "name": "generate_image",
  "parameters": {
    "prompt": "A beautiful landscape with mountains and a lake"
  }
}

Podcast Generation

{
  "name": "generate_podcast",
  "parameters": {
    "prompt": "The future of artificial intelligence",
    "duration": 5,
    "name1": "Mark",
    "voice1": "Thomas",
    "name2": "Sophia",
    "voice2": "Emily"
  }
}

Think Tool

{
  "name": "think_tool",
  "parameters": {
    "input": "What are the implications of quantum computing?"
  }
}

Project Structure

• main.py: Main FastAPI application and MCP tools implementation

• sse.py: Server-Sent Events (SSE) implementation

• pyproject.toml: Project metadata and dependencies

• requirements.txt: Basic dependencies list

Dependencies

• FastAPI: Web framework for building APIs

• MCP: Model Context Protocol implementation

• OpenAI: Client for Azure OpenAI services

• Uvicorn: ASGI server for running FastAPI applications

• Requests: HTTP library for API calls

License

[Specify your license here]

Contributing

[Instructions for contributing to the project]