modelcontextprotocol
CLI tool and utilities for scaffolding Model Context Protocol (MCP) projects with enhanced logging
Create production-ready MCP servers and clients in seconds with built-in loguru logging and optional PostHog analytics.
Features
- Quick Scaffolding - Generate MCP projects instantly
- Enhanced Logging - Beautiful logs with loguru out of the box
- Analytics - Optional PostHog integration for usage tracking
- Beautiful CLI - Rich terminal UI with helpful prompts
- Best Practices - Templates follow MCP best practices
- uvx Compatible - No installation needed with uvx
Quick Start
With uvx (No Installation)
# Interactive mode
uvx modelcontextprotocol create
# Direct creation
uvx modelcontextprotocol create my-server --type server
With pip/uv
# Install
pip install modelcontextprotocol
# or
uv pip install modelcontextprotocol
# Create a project
modelcontextprotocol create
# or
mcp-create server my-weather-server
📖 Usage
Interactive Mode
Simply run without arguments for an interactive experience:
modelcontextprotocol create
You'll be prompted for:
- Project name
- Project type (server/client)
- Template type (basic/advanced)
- Project path
Command Line Mode
# Create a basic server
mcp-create server my-server
# Create an advanced server with PostHog
mcp-create server my-server \
--template advanced \
--posthog-key YOUR_KEY
# Create a client
mcp-create client my-client
# Specify custom path
mcp-create server my-server --path ./projects/my-server
Environment Variables
# PostHog configuration
export POSTHOG_API_KEY="your-api-key"
export POSTHOG_HOST="https://app.posthog.com"
# Now create with analytics
mcp-create server my-server --template advanced
Generated Project Structure
Basic Server
my-server/
├── server.py # Main server file with loguru
├── pyproject.toml # Project configuration
├── .gitignore # Git ignore rules
└── README.md # Project documentation
Server Code (Basic)
from mcp.server.fastmcp import FastMCP
from loguru import logger
# Configure logging
logger.add("my-server.log", rotation="10 MB", level="INFO")
logger.info("Initializing my-server MCP server")
# Initialize server
mcp = FastMCP("my-server")
@mcp.tool()
async def example_tool(text: str) -> str:
"""An example tool that processes text."""
logger.info(f"Processing text: {text}")
result = f"Processed: {text}"
logger.debug(f"Result: {result}")
return result
if __name__ == "__main__":
logger.info("Starting my-server server")
mcp.run()
Advanced Server Features
The advanced template includes:
- Error logging to separate file
- HTTP client integration with httpx
- PostHog analytics tracking (optional)
- Graceful shutdown handling
- Enhanced error tracking
Templates
Basic Template
Perfect for simple MCP servers:
- Loguru logging to file
- Example tool and resource
- Clean structure
Advanced Template
For production servers:
- Dual logging (info + errors)
- HTTP client with retry logic
- PostHog analytics integration
- Error tracking
- Graceful shutdown
Logging with Loguru
All generated projects use loguru for beautiful, structured logging:
logger.info("Information message")
logger.success("Success message")
logger.warning("Warning message")
logger.error("Error message")
logger.debug("Debug message")
Logs are automatically:
- Color-coded in terminal
- Saved to files with rotation
- Formatted consistently
- Performance optimized
PostHog Analytics (Optional)
Track your MCP server usage:
# Automatically included in advanced template
posthog.capture(
distinct_id="server",
event="tool_called",
properties={"tool_name": "example_tool"}
)
Development
After creating your project:
cd my-server
# Create virtual environment
uv venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
# Install dependencies
uv pip install -e .
# Run your server
python server.py
Examples
Create Weather Server
mcp-create server weather-server --template advanced
cd weather-server
# Edit server.py to add weather API integration
python server.py
Create Database Client
mcp-create client db-client
cd db-client
# Edit client.py to connect to your MCP server
python client.py
With Analytics
export POSTHOG_API_KEY="phc_..."
mcp-create server analytics-server --template advanced
# PostHog tracking automatically included
Telemetry
This tool collects anonymous usage analytics to improve the user experience. No personal information or project details are collected.
To disable telemetry:
export MODELCONTEXTPROTOCOL_TELEMETRY=false
See TELEMETRY.md for full details.
Contributing
Contributions are welcome! This package helps developers:
- Get started with MCP quickly
- Follow best practices
- Include production-ready logging
- Track usage metrics (anonymous, opt-out available)
Package Contents
cli.py- CLI interface with rich promptstemplates/- Server and client templatesanalytics.py- PostHog integration- Additional utilities for MCP development
Resources
License
MIT License - See LICENSE file for details
Acknowledgments
- Built on top of the official MCP Python SDK
- Uses loguru for beautiful logging
- Inspired by create-react-app and similar scaffolding tools
Made for the MCP community
# Get started now!
uvx modelcontextprotocol create
Metadata
Release files for modelcontextprotocol 1.0.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| modelcontextprotocol-1.0.1.tar.gz | 15.9 kB | Without provenance | Details for modelcontextprotocol-1.0.1.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| modelcontextprotocol-1.0.1-py3-none-any.whl | Python 3 | none | any | Details for modelcontextprotocol-1.0.1-py3-none-any.whl |
Total release size: 40.9 kB
Release files / modelcontextprotocol-1.0.1.tar.gz
| Download URL | modelcontextprotocol-1.0.1.tar.gz |
|---|---|
| Size | 15.9 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
0d552129b5cd24241fdfee91182e231000c988935ee0620e4e71b3d7dc438b01
|
|
BLAKE2b-256 checksum How to use checksums |
0e2ac3d213769c64bc24a24dc0a57985fb42e5ebfe0b2fda4b26bb6e196df9f1
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.13.2
|
Release files / modelcontextprotocol-1.0.1-py3-none-any.whl
| Download URL | modelcontextprotocol-1.0.1-py3-none-any.whl |
|---|---|
| Size | 25.1 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
a72db01d26e50ed4da935efcaedc151b89dff93e1a6d6b91616db4c443ca2efd
|
|
BLAKE2b-256 checksum How to use checksums |
ea4bf22e56b5e73761d73ae616458742b984facfc7c0c81c8adab3072e1a94da
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.1.0 CPython/3.13.2
|
Security for modelcontextprotocol 1.0.1
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.