Skip to main content
Glama

MCP Project Initializer

An intelligent MCP (Model Context Protocol) server that automates the setup of new AI-powered MCP server development projects. This tool acts as a conversational guide through any standard MCP client to set up projects with necessary context, rules, and documentation for AI-assisted development.

Features

  • šŸ¤– Conversational Project Setup - Interactive step-by-step project initialization

  • šŸ“‹ AI-Enhanced PRD Generation - Transform basic concepts into comprehensive specifications

  • šŸ”§ Technology-Specific Context - Automatically downloads SDK documentation and best practices

  • šŸ“š Development Rules Integration - Includes coding standards and AI-optimized guidelines

  • šŸŽÆ Context-Based Development - Prepares projects for AI agents to implement with creativity

  • šŸ›”ļø MCP Protocol Compliant - Full compatibility with MCP clients and standards

Quick Start

Installation

# Clone the repository git clone <repository-url> cd mcp-initializer # Install dependencies npm install # Build the project npm run build

Using with MCP Clients

Windsurf IDE Configuration

Add this server to your Windsurf MCP settings:

{ "mcpServers": { "mcp-project-initializer": { "command": "node", "args": ["/path/to/mcp-initializer/build/index.js"], "description": "AI-powered project initialization server" } } }

Generic MCP Client Configuration

For any MCP client that supports STDIO transport:

{ "name": "mcp-project-initializer", "command": "node", "args": ["/path/to/mcp-initializer/build/index.js"], "transport": "stdio" }

Usage

Starting a New Project

  1. Start the conversation: Use the start_mcp_project tool

  2. Set project name: Use set_project_name with your desired project name

  3. Choose directory: Use set_project_directory with an absolute path

  4. Select technology: Use set_project_technology (typescript or python)

  5. Provide concept: Use set_project_description with a high-level overview

  6. Add documentation (optional): Use add_project_documentation for additional context

  7. Setup foundation: Use setup_project_foundation to create the project structure

  8. Generate context: Use generate_mcp_server to prepare for AI implementation

Example Conversation Flow

User: Use start_mcp_project AI: šŸš€ Welcome! I'll help you create a new MCP Server project... User: Use set_project_name with "task-manager-mcp" AI: āœ… Great! Project name set to: task-manager-mcp... User: Use set_project_directory with "/Users/yourname/Projects" AI: āœ… Perfect! Project directory set... User: Use set_project_technology with "typescript" AI: āœ… Excellent! Technology set to: typescript... User: Use set_project_description with "Help users manage daily tasks with reminders" AI: āœ… Perfect! Description captured... User: Use setup_project_foundation AI: šŸš€ Setting up project foundation... āœ“ Downloaded essential MCP documentation... User: Use generate_mcp_server AI: šŸŽ‰ Your Project is Ready for AI Implementation!

Project Structure Created

When you run the MCP Project Initializer, it creates:

your-project/ ā”œā”€ā”€ README.md # Project overview ā”œā”€ā”€ CLAUDE.md # AI development guidance ā”œā”€ā”€ IMPLEMENTATION.md # Detailed implementation guide ā”œā”€ā”€ PRD.md # Product Requirements Document ā”œā”€ā”€ package.json # Dependencies and scripts ā”œā”€ā”€ tsconfig.json # TypeScript configuration ā”œā”€ā”€ .gitignore # Git ignore rules ā”œā”€ā”€ .windsurf/ │ └── rules/ # Development best practices │ ā”œā”€ā”€ general.md # General coding standards │ ā”œā”€ā”€ typescript.md # TypeScript-specific rules │ └── mcp.md # MCP development patterns ā”œā”€ā”€ docs/ │ └── external/ # Downloaded documentation │ ā”œā”€ā”€ llms-full.txt # MCP client compatibility │ └── typescript-sdk-README.md # SDK documentation ā”œā”€ā”€ src/ # Source code directory └── tests/ # Test directory

Key Features

AI-Enhanced Development

  • Context-Rich Setup: Downloads essential MCP documentation automatically

  • Best Practices Integration: Includes technology-specific coding standards

  • PRD Enhancement: AI agents expand basic concepts into detailed specifications

  • Step-by-Step Guidance: Clear implementation instructions for AI agents

Technology Support

  • TypeScript: Full Node.js MCP server setup with ES modules

  • Python: Complete Python MCP server configuration

  • Extensible: Easy to add support for additional technologies

MCP Protocol Compliance

  • Tools-Only Design: No prompts - fully compatible with tools-only clients

  • Conversational State: Maintains conversation flow across tool calls

  • Error Handling: Comprehensive validation and user guidance

  • Standard Transport: Uses STDIO for maximum compatibility

Development

Building from Source

# Install dependencies npm install # Build the project npm run build # Run in development mode npm run dev # Type checking npm run typecheck # Linting npm run lint

Project Structure

mcp-initializer/ ā”œā”€ā”€ src/ │ ā”œā”€ā”€ index.ts # MCP server main entry │ ā”œā”€ā”€ project-initializer.ts # Core initialization logic │ └── types.ts # TypeScript type definitions ā”œā”€ā”€ templates/ │ └── rules/ # Development rule templates │ ā”œā”€ā”€ typescript.md # TypeScript best practices │ └── python.md # Python best practices ā”œā”€ā”€ build/ # Compiled output └── docs/ # Project documentation

Requirements

  • Node.js: >= 18.0.0

  • MCP Client: Any MCP-compatible client (Windsurf, Claude Desktop, etc.)

  • Operating System: macOS, Linux, Windows

Contributing

  1. Fork the repository

  2. Create a feature branch

  3. Make your changes following the coding standards

  4. Test with a real MCP client

  5. Submit a pull request

License

MIT License - see LICENSE file for details.

Support

For issues and questions:

  • Check the documentation in /docs

  • Review the generated IMPLEMENTATION.md for guidance

  • Open an issue on the project repository


Ready to create AI-powered projects? Configure this MCP server in your client and start building! šŸš€

-
security - not tested
A
license - permissive license
-
quality - not tested

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Syndicats/mcp-initializer'

If you have feedback or need assistance with the MCP directory API, please join our Discord server