About mcpc
mcpc is a command-line scaffolding generator for developers starting MCP server projects. It creates TypeScript or Python project structures with package-manager options, setup files, dependency installation, and server testing support for Python.
Key features
- 01Generate TypeScript or Python server projects
- 02Choose supported package managers
- 03Install project dependencies automatically
- 04Validate system dependencies
- 05Initialize a Git repository
- 06Test Python servers without Claude
Use cases
- 01Create a starter MCP server project
- 02Set up a project with a chosen language and package manager
- 03Check a generated Python server without Claude
MCP support
Generates project scaffolding for MCP servers, including the structure and configuration needed to build and run a server.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEmcpc
MCP (Model Context Protocol) Server Template Generator
Introduction
mcpc is a command-line tool that generates scaffolding for MCP (Model Context Protocol) server projects. It helps you quickly set up a properly structured project with all necessary files and configurations.
Features
- Generate MCP server templates for TypeScript or Python
- Support for multiple package managers (pnpm, yarn, npm for TypeScript; uv for Python)
- Automatic dependency installation
- System dependency validation
- Git repository initialization
- Complete project structure following official MCP documentation
- Python test mode for verifying server functionality without Claude
- Configuration files and best practices included
Installation
Prerequisites
- Rust and Cargo (can be installed via rustup)
Build and Install
Using Make:
# Build and install in one step
make install
Or using Cargo directly:
# Install from local repository
cargo install --path .
Usage
Basic usage:
mcpc project_name [options]
Options:
-l, --language: Programming language to use (py/python, ts/typescript, default: typescript)-t, --tool: Package manager tool to use:- For TypeScript: pnpm (default), yarn, npm
- For Python: uv (default)
Examples:
# Create a TypeScript project named 'weather-api' using pnpm
mcpc weather-api -l ts -t pnpm
# Create a Python project named 'mcp-server' using uv
mcpc mcp-server -l py -t uv
Generated Project Structure
TypeScript Project
project_name/
├── .gitignore
├── .prettierignore
├── .prettierrc
├── package.json
├── README.md
├── tsconfig.json
├── build/
└── src/
└── index.ts
Python Project
project_name/
├── .gitignore
├── pyproject.toml
├── README.md
├── requirements.txt
├── server.py
└── .venv/
Using Generated Projects
Python
# Activate virtual environment
source .venv/bin/activate # On Windows: .venv\Scripts\activate
# Install dependencies (if not already installed)
uv pip install -r requirements.txt
# Test server functionality without Claude
python server.py --test
# Run server for Claude integration
python server.py
TypeScript
# Install dependencies (if not already installed)
pnpm install # or: yarn / npm install
# Build the project
pnpm run build # or: yarn build / npm run build
# Run server
node build/index.js
Claude for Desktop Integration
To integrate with Claude for Desktop, configure your server in Claude's configuration file:
{
"mcpServers": {
"weather": {
"command": "uv", // or "node" for TypeScript
"args": [
"--directory",
"/ABSOLUTE/PATH/TO/PROJECT",
"run",
"server.py" // or "build/index.js" for TypeScript
]
}
}
}
Development
Available Make Commands
make # Build the project (same as 'make build')
make build # Build the project in debug mode
make release # Build the project in release mode
make install # Build in release mode and install
make run # Run the project in debug mode
make run-release # Run the project in release mode
make test # Run tests
make docs # Generate and open documentation
make clean # Clean build artifacts
make fmt # Format code with rustfmt
make check # Check for compilation errors
make clippy # Run Clippy lints
Build from Source
git clone https://github.com/yourusername/mcpc.git
cd mcpc
make install
License
This project is licensed under the MIT License - see the LICENSE file for details.
Comments
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.