Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@random-number-servergenerate a random number using weather data from New York"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
random-number-server
MCP server to generate random numbers using the national weather data as seeds.
Build Instructions
Local Development Build
# Install uv if not already installed
curl -LsSf https://astral.sh/uv/install.sh | sh
# Clone the repository
git clone https://github.com/nobelk/random-number-server.git
cd random-number-server
# Install dependencies and build the project
uv sync
# Install in editable mode for development
uv pip install -e .Docker Build
# Build the Docker image
docker build -t random-number-server:latest .
# Or use Docker Compose to build
docker-compose buildQuick Start
Using Docker Compose (Recommended)
# Build and run the server
docker-compose up -d
# View logs
docker-compose logs -f
# Stop the server
docker-compose downUsing uv directly
# Install dependencies
uv sync
# Run the server
uv run src/random_server.pyUnit Tests
The project includes comprehensive unit tests for both core modules with 86% code coverage.
Running Tests
# Install dependencies
uv sync
# Run all tests
uv run pytest
# Run tests with verbose output
uv run pytest -v
# Run tests with coverage report
uv run pytest --cov=src --cov-report=term-missing
# Run specific test files
uv run pytest tests/test_random_number_generator.py
uv run pytest tests/test_random_server.pyTest Coverage
src/RandomNumberGenerator.py: 83% coverage (13 tests)
src/random_server.py: 92% coverage (17 tests)
Total: 86% coverage (30 tests)
Tests cover:
Initialization and configuration
Random number generation algorithms
Weather API integration
Error handling and edge cases
FastMCP tool registration and execution
Concurrent request handling
Docker Setup
The project includes Docker and Docker Compose configurations for easy deployment.
Docker Image
Base: Python 3.13 Alpine (optimized for size)
Size: ~110MB
Security: Runs as non-root user
Build: Multi-stage build for optimization
Docker Compose
# Production
docker-compose up -d
# Development (with live reload)
docker-compose -f docker-compose.yml -f docker-compose.dev.yml up
# Run tests in container
docker-compose run --rm --entrypoint /app/.venv/bin/python random-server -m pytestSee README_DOCKER.md for detailed Docker instructions.
MCP Configuration
Run the MCP server locally
uv --directory /ABSOLUTE/PATH/TO/PARENT/FOLDER/random-number-server run src/random_server.pyConfigure Claude Desktop
Edit ~/Library/Application\ Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"weather": {
"command": "/Users/Nobel.Khandaker/.pyenv/shims/uv",
"args": [
"--directory",
"/Users/Nobel.Khandaker/sources/random-number-server",
"run",
"src/random_server.py"
]
}
}
}This server cannot be installed
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.