create-python-server
Language:
Python
Stars:
383
Forks:
71
MCP Create Server
Create Model Context Protocol (MCP) server projects with no build configuration.
Quick Overview
# Using uvx (recommended)
uvx create-mcp-server
# Or using pip
pip install create-mcp-server
create-mcp-server
You don't need to install or configure any dependencies manually. The tool will set up everything you need to create an MCP server.
Creating a Server
You'll need to have UV >= 0.4.10 installed on your machine.
To create a new server, run either of these commands:
Using uvx (recommended)
uvx create-mcp-server
Using pip
pip install create-mcp-server
create-mcp-server
It will walk you through creating a new MCP server project. When complete, you'll have a new directory with this structure:
my-server/
├── README.md
├── pyproject.toml
└── src/
└── my_server/
├── __init__.py
├── __main__.py
└── server.py
No configuration or complicated folder structures, only the files you need to run your server.
Once installation is done, you can start the server:
cd my-server
uv sync --dev --all-extras
uv run my-server
Features
- Simple command-line interface for creating new projects
- Auto-configures Claude Desktop app integration when available
- Uses uvx for fast, reliable package management and project creation
- Sets up basic MCP server structure
- Uses the Model Context Protocol Python SDK for the server project
Philosophy
-
Zero Configuration: No need to manually set up project structure or dependencies.
- **Best Practices:** Follows Python packaging standards and MCP server patterns.
-
Batteries Included: Comes with everything needed to start building an MCP server.
License
Create MCP Server is open source software licensed as MIT.
Publisher info
Model Context Protocol
An open protocol that enables seamless integration between LLM applications and external data sources and tools.
More MCP servers built with Python
Create, backtest, and execute trades directly in one chat box. The Composer MCP Server gives LLMs the power to backtest investment ideas and execute automated trading strategies. Trade across stocks, ETFs, and crypto directly in Claude.
An MCP to generate presentations with AI. Create and edit PowerPoint presentations with AI.
The PaddleOCR MCP server brings enterprise-grade OCR and document parsing capabilities to AI applications. Built on PaddleOCR — a proven solution with 50,000+ GitHub stars, deeply integrated by leading projects like MinerU, RAGFlow, and OmniParser— with targeted optimizations based on the MCP concept.