nestjs-starter

Production-ready NestJS boilerplate with JWT auth, PostgreSQL/Prisma, AWS S3/SES, Bull/Redis queues, Docker/K8s support, and MCP integration for AI capabilities

Installation

Run this command in your terminal to add the MCP server to Claude Code.

Run in terminal:

View docs

Command

claude mcp add --transport stdio hmake98-nestjs-starter node dist/main.js \
  --env REDIS_URL="Redis connection string for Bull queues" \
  --env S3_BUCKET="AWS S3 bucket name" \
  --env SES_REGION="AWS SES region" \
  --env MCP_ENABLED="true - enable MCP integration" \
  --env DATABASE_URL="Database connection string (PostgreSQL)" \
  --env MCP_LOG_LEVEL="info - MCP logging level" \
  --env SES_FROM_ADDRESS="Default sender email for SES"

How to use

NestJS Starter ships with integrated Model Context Protocol (MCP) support, enabling AI-powered tooling, resources, and prompts to be used alongside your API. The MCP features are exposed via the NestJS API and a dedicated MCP playground. You can experiment with the AI tools directly in the playground, or integrate MCP prompts into your own endpoints to perform tasks such as data augmentation, reasoning, or automated content generation. The MCP integration is designed to work with the server’s existing authentication, RBAC, and queueing systems, so you can test AI-assisted workflows in a production-like environment. Access the MCP Playground at /mcp/playground and review the available tools, resources, and prompts in your project’s MCP configuration.

How to install

Prerequisites:

Node.js v20 or newer
Yarn v1.x+ (or npm)
Docker (optional for containerized setup)

Clone the repository

git clone https://github.com/hmake98/nestjs-starter.git
cd nestjs-starter

Install dependencies

# Using Yarn
yarn install
# Or with npm
npm install

Configure environment

# Copy environment template if available and edit as needed
cp .env.example .env

Build the application

# Compile TypeScript to JavaScript (if using a build step)
yarn build
# If using npm
npm run build

Run in development or production mode

# Development run (hot reload if configured)
yarn dev
# Production run (compiled output)
yarn start

Optional: Run with Docker (if provided)

docker-compose up --build

Additional notes

Environment variables are configurable in .env. Common MCP-related settings include enabling MCP features (MCP_ENABLED) and pointing to your database and Redis instances for queues. If you run locally, ensure PostgreSQL and Redis are up and accessible. The MCP Playground exposes several AI tools; refer to the MCP documentation within the project for details on each tool, resource, and prompt. If you encounter API route 404s for MCP endpoints, verify that MCP is enabled and that the server has fully started (check logs for MCP startup messages). For deployment, consider containerized deployment with Docker Compose as described in the README, and ensure you expose the MCP endpoints to your gateway or reverse proxy as needed.

Related MCP Servers

mcpcan

715

MCPCAN is a centralized management platform for MCP services. It deploys each MCP service using a container deployment method. The platform supports container monitoring and MCP service token verification, solving security risks and enabling rapid deployment of MCP services. It uses SSE, STDIO, and STREAMABLEHTTP access protocols to deploy MCP。

phpMyFAQ

610

phpMyFAQ - Open Source FAQ web application for PHP 8.3+ and MySQL, PostgreSQL and other databases

agentscope-runtime

491

A production-ready runtime framework for agent apps with secure tool sandboxing, Agent-as-a-Service APIs, scalable deployment, full-stack observability, and broad framework compatibility.

mcp-for-argocd

335

An implementation of Model Context Protocol (MCP) server for Argo CD.

magg

130

Magg: The MCP Aggregator

sandbox

A Model Context Protocol (MCP) server that enables LLMs to run ANY code safely in isolated Docker containers.