Provides containerization support for the MCP server, allowing it to be built and run as a Docker container with exposed endpoints.
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., "@MCP Server Demoshow me how to connect this server to Claude Desktop"
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.
CORRER APP
Instalar dependencias
uv sync
Correr APP
uv run server.py
DOCKER
docker build -t mcp-server-demo .
docker run -p 8000:8000 --name app-mcp-server mcp-server-demo
ADICIONAL
Instalar librerias
pip install "any"
Instalar en claude desktop
uv run mcp install server.py
Correr MCP inspector
uv run mcp install server.py
CONEXION:
Ejecutando el Script
{
"mcpServers": {
"mcp-server-demo": {
"command": "C:\\Users\\my-user\\.local\\bin\\uv.EXE",
"args": [
"run",
"--with",
"mcp[cli]",
"mcp",
"run",
"C:\\Users\\my-path\\mcp-server-demo\\server.py"
]
}
}
}
Ejecutando el servidor
{
"mcpServers": {
"mcp-server-docker": {
"url": "http://0.0.0.0:8000/mcp/"
}
}
}
REFERENCIAS
Python SDK for MCP - SDK oficial de Python para Model Context Protocol
