About mcp_starter_cli
mcp_starter_cli is a command-line tool for scaffolding, running, and testing local MCP servers with Node.js or Python. It combines key injection, live logs, and Claude Desktop linking for developers building and debugging servers.
Key features
- 01Scaffold Node.js and Python servers
- 02Run and test servers locally
- 03Inject OpenAI and Claude API keys
- 04View live logs and errors
- 05Link with Claude Desktop
- 06Lint JavaScript and transpile TypeScript
Use cases
- 01Create a starter MCP server project
- 02Debug a locally running server
- 03Test a server with Claude Desktop
MCP support
It scaffolds, runs, and tests local MCP servers. Claude Desktop can be linked for local agent testing.
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 READMEmcp_starter_cli
Introduction
mcp_starter_cli is a powerful Command Line Interface (CLI) tool designed to simplify the process of scaffolding, running, and testing MCP servers locally using Node.js or Python. It integrates seamlessly with Claude and OpenAI API keys for enhanced functionality. Additionally, it supports auto-linking to Claude Desktop for local agent testing and includes features like live error display and support for auto-linting and TypeScript transpilation.
Features
- CLI Interface: Easily scaffold, run, and deploy MCP servers.
- API Key Injection: Dynamically inject OpenAI or Claude API keys as needed.
- Server Logging & Error Display: Monitor server logs in real-time with live error display for quick debugging.
- Claude Desktop Integration: Automatically link to Claude Desktop for local agent testing.
- Auto-linting and TS Transpilation: Built-in support for linting JavaScript/TypeScript code and transpiling TypeScript.
Installation Instructions
Prerequisites
Ensure you have Node.js installed on your system. You can download it from nodejs.org.
Install mcp_starter_cli
You can install the CLI tool globally using npm:
npm install -g mcp_starter_cli
Alternatively, if you prefer to use Yarn:
yarn global add mcp_starter_cli
Usage Examples
Scaffold a New Project
To create a new MCP server project, run:
mcp_starter_cli scaffold my-mcp-project --template nodejs
or for Python projects:
mcp_starter_cli scaffold my-python-mcp-project --template python
Run the Server Locally
Navigate to your project directory and start the server:
cd my-mcp-project
mcp_starter_cli run
For Python:
cd my-python-mcp-project
mcp_starter_cli run
Inject API Keys
To inject OpenAI or Claude API keys, use:
mcp_starter_cli config set openai-key YOUR_OPENAI_API_KEY
mcp_starter_cli config set claude-key YOUR_CLAUDE_API_KEY
View Server Logs
Monitor the server logs in real-time with live error display:
mcp_starter_cli logs
API Documentation
For detailed API documentation and advanced usage, please refer to the API Docs.
License
mcp_starter_cli is open-source software licensed under the MIT License. For more details, see the LICENSE file.
Feel free to contribute to this project or report any issues via our GitHub repository. Happy coding! 🚀
This README provides a comprehensive overview of the `mcp_starter_cli` tool, including its features, installation instructions, usage examples, and licensing information. Make sure to replace placeholders like `your-repo` with your actual GitHub repository details.
## ⚠️ Development Status
This library is currently in early development. Some tests may be failing with the following issues:
Contributions to fix these issues are welcome! Please submit a pull request if you have a solution.
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.