shubhradeep23/simple-mcp-server

Babaganoooush MCP Server

A simple Model Context Protocol (MCP) server that returns the phrase "what a babaganoooush" using Python's FastMCP library with HTTP transport.

Features

• Simple MCP server with one tool: get_phrase
• HTTP transport for client connectivity
• Docker containerization support
• Health checks included
• Easy integration with Cursor

Prerequisites

• Python 3.10 or higher
• Docker and Docker Compose (for containerized deployment)

Installation

Method 1: Direct Python Installation

1. Install dependencies:

   pip install -r requirements.txt
   

2. Run the server:

   python server.py
   

Method 2: Using uv (Recommended)

1. Install uv:

   pip install uv
   

2. Create virtual environment and install dependencies:

   uv venv myenv
   source myenv/bin/activate  # On Windows: myenv\Scripts\activate
   uv pip install -r requirements.txt
   

3. Run the server:

   python server.py
   

Running the Server

Direct Python Execution

python server.py

The server will start and be available at: http://127.0.0.1:8000/mcp

Docker Deployment

1. Build and run with Docker Compose:

   docker-compose up --build
   

2. Run in background:

   docker-compose up -d --build
   

3. Stop the server:

   docker-compose down
   

Accessing the MCP Server

Via HTTP Client

You can test the server using curl:

curl http://localhost:8000/mcp

Via Python Client

import asyncio
from fastmcp import Client

async def main():
    async with Client("http://127.0.0.1:8000/mcp") as client:
        result = await client.call_tool("get_phrase")
        print(result)

asyncio.run(main())

Expected output: what a babaganoooush

Cursor Integration

To use this MCP server with Cursor, add the following configuration to your Cursor MCP settings:

{
  "mcpServers": {
    "babaganoooush": {
      "url": "http://127.0.0.1:8000/mcp"
    }
  }
}

API Reference

Tools

get_phrase()

• Description: Returns the phrase "what a babaganoooush"
• Parameters: None
• Returns: str - The phrase "what a babaganoooush"

Health Checks

The Docker container includes health checks that verify the server is responding correctly:

• Interval: 30 seconds
• Timeout: 10 seconds
• Retries: 3
• Start Period: 40 seconds

Troubleshooting

Server won't start

• Ensure Python 3.10+ is installed
• Check if port 8000 is available
• Verify all dependencies are installed

Docker issues

• Ensure Docker and Docker Compose are installed
• Check if port 8000 is not already in use
• Try rebuilding the image: docker-compose up --build --force-recreate

Connection issues

• Verify the server is running: curl http://localhost:8000/mcp
• Check firewall settings
• Ensure the correct URL is used in client configuration

Development

To modify the server:

1. Edit server.py to add new tools or modify existing ones
2. Update requirements.txt if new dependencies are needed
3. Rebuild the Docker image if using containerized deployment

License

This project is open source and available under the MIT License.