mcpField
H
Hello World (UV Runtime)

Hello World (UV Runtime)

VerifiedLocal
github.com/modelcontextprotocolDeveloper Tools2.2kUpdated 27w ago

About Hello World (UV Runtime)

Hello World UV Runtime is a minimal MCP server example that uses the UV runtime. It is aimed at developers learning how Claude Desktop extensions are packaged, and it contrasts the approach with the traditional Python runtime.

Key features

  1. 01Configured with server.type set to uv
  2. 02Dependencies declared in pyproject.toml, not bundled
  3. 03Small bundle size of about 2 KB
  4. 04Dependencies resolved automatically through uv run

Use cases

  1. 01Learning the basic structure of an MCP server
  2. 02Starting template for a Claude Desktop extension
  3. 03Comparing UV and Python runtime packaging

MCP support

The example exposes a say_hello MCP tool that greets a person by name, and it is installed in Claude Desktop as an extension.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Hello World UV Runtime Example

This example demonstrates a minimal MCP server using UV runtime.

What is UV Runtime?

UV runtime lets Claude Desktop automatically manage Python and dependencies for your extension:

  • Downloads the correct Python version for the user's platform
  • Creates an isolated virtual environment
  • Installs dependencies from pyproject.toml
  • Works cross-platform (Windows, macOS, Linux) without user setup

Structure

hello-world-uv/
├── manifest.json       # server.type = "uv"
├── pyproject.toml      # Dependencies listed here
├── .mcpbignore        # Exclude build artifacts
└── src/
    └── server.py       # MCP server implementation

Key Differences from Python Runtime

UV Runtime (this example):

  • server.type = "uv"
  • No bundled dependencies
  • mcp_config uses uv run to auto-resolve deps from pyproject.toml
  • Small bundle size (~2 KB)
  • Works on any platform

Python Runtime (traditional):

  • server.type = "python"
  • Must bundle dependencies in server/lib/
  • Requires mcp_config with PYTHONPATH
  • Larger bundle size
  • Only works with pure Python (no compiled deps)

Installing

mcpb pack

Install the generated .mcpb file in Claude Desktop.

Testing Locally

# Install dependencies
uv sync

# Run server
uv run src/server.py

Tools

  • say_hello - Greets a person by name

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.