Provides templates for designing GitHub workflow plans including branch strategies, PR templates, and CI/CD configurations
Supports generating API architecture plans with MongoDB integration as a database option
Supports generating API architecture plans with MySQL integration as a database option
Supports configuration of deployment targets for GitHub workflows when Netlify is specified
Provides templates for Node.js-based TypeScript projects, enabling proper configuration and setup
Supports setup planning for TypeScript frontend libraries with React components
Offers specialized templates for creating comprehensive TypeScript project setups and API architectures following modern development standards
Supports configuration of deployment targets for GitHub workflows when Vercel is specified
TypeScript Prompt MCP Server
A Model Context Protocol (MCP) server that provides pre-defined prompt templates for AI assistants, allowing them to generate comprehensive plans for TypeScript projects, API architectures, and GitHub workflows.
🌟 Overview
This MCP server provides a set of prompt templates that can be used by AI assistants to generate detailed, structured responses for TypeScript project planning. It offers templates for:
- Creating comprehensive API architecture plans
- Setting up new TypeScript projects with best practices
- Generating GitHub workflow configurations
This MCP was specifically created to work with the Local Dev MCP, forming a powerful combination where the Prompt MCP generates detailed project plans and the Local Dev MCP executes them. Together, they create a seamless workflow for AI-assisted TypeScript project development.
Each prompt template is designed to ensure AI assistants provide consistent, high-quality, and detailed project plans following modern TypeScript development standards.
🚀 Features
- 🏗️ API Architecture Planning: Generate comprehensive API architecture plans including layers, folder structures, and database schemas
- 🚀 Project Setup: Create detailed setup plans for new TypeScript projects with appropriate dependencies and configurations
- 🔄 GitHub Workflow: Design GitHub workflow plans with branch strategies, PR templates, and CI/CD configurations
- 🛠️ Customization: Each prompt accepts parameters to tailor the generated plans to your specific needs
- ⚡ Consistent Output: Ensures AI assistants provide structured, detailed responses that follow best practices
📋 Prerequisites
- Node.js (v14 or higher)
- npm or yarn
🔧 Installation
- Clone the repository
- Install dependencies
- Set up environment variables
🎮 Usage
Development Mode
This starts the MCP server in development mode with hot reload.
Production Mode
Or use the shorthand:
🔗 Integration with Local Dev MCP and Claude Desktop
To add this MCP server to Claude Desktop:
- Start the MCP server Make sure your server is running locally.
- Open Claude Desktop settings
- Launch Claude Desktop
- Click on your profile picture or icon in the top right
- Select "Settings" from the dropdown menu
- Navigate to Extensions settings
- In the Settings sidebar, click on "Extensions"
- Select "Add Custom MCP"
4.1 Configure the MCP connection
- Name:
TypeScript Prompt MCP
(or any name you prefer) - URL: Enter the URL where your MCP server is running (e.g.,
http://localhost:3000
for local development) - Click "Add MCP"
4.2 Alternative: Configure the MCP connection via command
- You first need to build the project and provide your full path to the compiled server
- Add the following to your Claude Desktop configuration:
- Enable the MCP
- Toggle the switch next to your newly added MCP to enable it
- Claude Desktop will attempt to connect to your MCP server
- Add Local Dev MCP
- Repeat steps 3-5 to also add the Local Dev MCP to Claude Desktop
- Having both MCPs enabled allows for a complete workflow from planning to implementation
- Verify connection
- Start a new conversation with Claude
- Ask Claude to help you plan a TypeScript project or API architecture
- Claude should now be able to use the prompt templates to provide detailed plans
- Then ask Claude to implement the plan using Local Dev MCP
Usage Examples with Claude
Once connected with both MCPs, you can ask Claude to:
- "Can you help me plan an API architecture for a TypeScript project called 'ecommerce-backend' with MongoDB and JWT authentication?" (uses this Prompt MCP)
- "I need a setup plan for a new TypeScript frontend library with React components" (uses this Prompt MCP)
- "Create a GitHub workflow plan for my TypeScript CLI project with automated testing and npm publishing" (uses this Prompt MCP)
- "Now implement the API project we just planned using the Local Dev MCP" (uses Local Dev MCP)
- "Set up the TypeScript project with the plan we created" (uses Local Dev MCP)
This combination of MCPs creates a powerful workflow where you can plan your project in detail and then implement it without leaving the Claude interface.
🧠 Available Prompts
The server exposes several prompts that can be used by AI assistants:
api-architecture
Generates a comprehensive architecture plan for a TypeScript API.
Parameters:
projectName
: Name of the API projectdatabase
: Database to use (postgres, mysql, mongodb, etc.)auth
: Authentication method (jwt, oauth, none)endpoints
: Comma-separated list of main API endpoints
new-project-setup
Generates a comprehensive setup plan for a new TypeScript project.
Parameters:
projectName
: Name of the projectprojectType
: Type of project (api, frontend, library, cli)features
: Key features or requirements separated by commas
github-workflow
Generates a GitHub workflow plan for a TypeScript project.
Parameters:
projectName
: Name of the projectciFeatures
: Comma-separated list of CI features (lint, test, build, etc.)deployTarget
: Deployment target (netlify, vercel, aws, azure, etc.)branchStrategy
: Branch strategy (gitflow, trunk, github-flow)
🔍 How It Works
The server creates an MCP server using the ModelContextProtocol SDK:
- It defines structured prompts with parameters using zod for validation
- Each prompt returns a formatted message that guides AI assistants in generating comprehensive plans
- The prompts include detailed instructions about what to include in the plans
- The server connects to Claude or other MCP-compatible AI assistants through a transport (typically stdio)
🛠️ Project Structure
⚙️ Development
Adding New Prompts
To add a new prompt template:
- Create a new file in the
src/prompts
directory - Define your prompt using the
mcpServer.prompt()
method - Add parameter validation using zod schemas
- Export your prompt in
src/prompts/index.ts
Example:
Environment Configuration
The server uses different environment files for development and production:
.env.development
- Used when running in development mode.env.production
- Used when running in production mode
Testing
Run the test suite with:
Linting and Formatting
📝 Notes for Deployment
When deploying to production:
- Ensure your
.env.production
file contains valid credentials if required - The build process will embed these credentials in the compiled code
- Use
npm run prod
to build and start the production server
📄 License
This project is licensed under the MIT License - see the LICENSE file for details.
Author
Gpaul | Faldin
This server cannot be installed
hybrid server
The server is able to function both locally and remotely, depending on the configuration or use case.
Provides pre-defined prompt templates for AI assistants to generate comprehensive plans for TypeScript projects, API architectures, and GitHub workflows.
Related MCP Servers
- AsecurityAlicenseAqualityA TypeScript server that enhances AI assistants' capabilities when working with Starwind UI components, providing tools for project initialization, component installation, documentation access, and more.Last updated -619TypeScriptMIT License
- -securityFlicense-qualityA Model Context Protocol implementation for managing and serving AI prompts with a TypeScript-based architecture in a monorepo structure.Last updated -28,526,5832TypeScript
- -securityFlicense-qualityProvides AI assistants with access to Payman's documentation, helping developers build integrations more efficiently through enhanced contextual support.Last updated -TypeScript
- AsecurityAlicenseAqualityA TypeScript-based Model Context Protocol toolkit that enables AI to interact with code files, manage translations, build projects, and search for files and code content.Last updated -33435TypeScriptMIT License