Skip to main content
nitrostack - AI Agents | SkillsLLM
Home AI Agents nitrostack The full-stack TypeScript framework to build, test, and deploy production-ready MCP servers and AI-native apps.
agentic-ai ai chatgpt chatgpt-apps claude
# Add to your Claude Code skills
git clone https://github.com/nitrocloudofficial/nitrostackGuides for using ai agents skills like nitrostack.
Documentation ·
Quick Start ·
Blog ·
NitroStudio ·
Discord
Quick Start
Prerequisites
1. Scaffold a new project
npx @nitrostack/cli init my-server
2. Start developing
cd my-server
npm install
npm run dev
Your MCP server is running. Connect it to any MCP-compatible client.
3. Open in NitroStudio
Once your project is scaffolded, open the same folder in NitroStudio for visual testing and debugging.
Download: https://nitrostack.ai/studio
Open your my-server project folder
Use NitroStudio to test tools, inspect payloads, and chat with your MCP server
Why NitroStack?
Building MCP servers today means stitching together boilerplate, reinventing authentication, and hoping your tooling scales. NitroStack gives you an opinionated, batteries-included framework so you can focus on what your server actually does.
Decorator-driven — Define tools, resources, and prompts with clean, declarative TypeScript decoratorsDependency injection — First-class DI container with singleton, transient, and scoped lifecyclesAuth built in — JWT, OAuth 2.1, and API key authentication out of the boxMiddleware pipeline — Guards, interceptors, pipes, and exception filters just like enterprise backends
Sign in with GitHub to leave a comment.
No comments yet. Be the first to share your thoughts!
Related Skills Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
claude-apps
mcp
mcp-client
mcp-server
mcp-servers
mcp-tools
mcpagents
mcpapps
model-context-protocol
modelcontextprotocol
First-time install walkthrough for Claude Code, Codex CLI, and ChatGPT.
UI Widgets — Attach React components to tool outputs for rich, interactive responses
Zod validation — End-to-end type safety from schema to runtime
NitroStudio — A dedicated desktop app for testing, debugging, and chatting with your server
See It in Action import { McpApp, Module, ToolDecorator as Tool, z, ExecutionContext } from '@nitrostack/core';
@McpApp({
module: AppModule,
server: { name: 'my-server', version: '1.0.0' }
})
@Module({ imports: [] })
export class AppModule {}
export class SearchTools {
@Tool({
name: 'search_products',
description: 'Search the product catalog',
inputSchema: z.object({
query: z.string().describe('Search query'),
maxResults: z.number().default(10)
})
})
@UseGuards(ApiKeyGuard)
@Cache({ ttl: 300 })
@Widget('product-grid')
async search(input: { query: string; maxResults: number }, ctx: ExecutionContext) {
ctx.logger.info('Searching products', { query: input.query });
return this.productService.search(input.query, input.maxResults);
}
}
One decorator stack gives you: API definition + validation + auth + caching + UI — zero boilerplate.
Ecosystem NitroStack is modular. Install only what you need:
The implementation workspace for NitroStack packages lives in typescript/
| Package | What it does | Install |
|:---|:---|:---|
| @nitrostack/corenpm i @nitrostack/core |
| @nitrostack/clinpm i -g @nitrostack/cli |
| @nitrostack/widgetsnpm i @nitrostack/widgets |
NitroStudio NitroStudio is a desktop app purpose-built for developing MCP servers. Open your project folder — it handles the dev server for you.
Real-time tool testing
Execute tools, inspect payloads, and debug request/response cycles.
Built-in AI chat
Talk to your MCP server through an integrated AI assistant.
Widget preview — Instantly visualize your interactive UI componentsHot reload — Changes reflect in real time as you develop
Documentation | Resource | Description |
|:---|:---|
| Getting Started | Installation, quick start, and first project |
| Server Concepts | Modules, DI, and architecture deep dive |
| Tools Guide | Defining tools, validation, annotations |
| Widgets Guide | Building interactive UI components |
| Authentication | JWT, OAuth 2.1, API key setup |
| CLI Reference | All CLI commands and options |
| Deployment | Production checklist, Docker, cloud platforms |
Community
Discord — Ask questions, share projects, get helpGitHub Discussions — Proposals, ideas, and Q&ATwitter / X — Announcements and updatesYouTube — Product demos and walkthroughsLinkedIn — Company news and updatesGitHub — Organization profile and open-source workBlog — Tutorials, deep dives, and release notes
Contributing We welcome contributions of all kinds — bug fixes, features, docs, and ideas. Read the Contributing Guide
Contributors
License
57,557
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
AI Agents ai-agents anthropic
The agent that grows with you
AI Agents ai ai-agent
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflows - all through natural language commands.
AI Agents
LLM inference in C/C++
AI Agents ggml
An open-source AI agent that brings the power of Gemini directly into your terminal.
AI Agents ai ai-agents
