Command Palette

Search for a command to run...

UnylyUnyly
Весь каталог

VibeServe

БесплатноНе проверен

A production-grade MCP server that turns natural language intent into fully-architected, accessible, production-ready UI code through a 7-step agentic pipeline.

GitHubEmbed

Описание

A production-grade MCP server that turns natural language intent into fully-architected, accessible, production-ready UI code through a 7-step agentic pipeline.

README

VibeServe

VibeServe v1.1

The Ultimate Agentic IDE, Orchestrator, and MCP Backend

CI PyPI Node.js React Python 3.10+ MCP License: MIT

What is VibeServe?

VibeServe is the first full-stack, fully-integrated AI development platform. It unifies a React-based AI IDE, a Node.js Orchestrator, and a Python MCP Server into a single cohesive system.

It transforms natural language intent into fully-architected, accessible, production-ready UI code — powered by a 7-step agentic pipeline, a fully aware context engine, and dynamic human-in-the-loop controls.

🏗️ architect → 💻 code → 🔍 review → ✅ verify → 🔄 iterate → 🧪 test → 🚀 deploy

Unified Repository Structure

This repository is a monorepo housing the three core pillars of the VibeServe ecosystem:

1. ide/ (The Front-End Client)

The VibeServe IDE (formerly Nexus-Alpha) is a Vite/React application acting as the command center. It features an interactive command palette, real-time agent trajectories, code editors, artifact previews, and full MCP tool visibility. It's fully WCAG AAA accessible and designed for extreme performance.

2. orchestrator/ (The Control Plane)

The VibeServe Orchestrator (formerly CodeNexus) is a high-performance Node.js backend. It coordinates agents, handles WebSockets for real-time streaming, runs deep security audits (AST analysis), and manages the lifecycle of the AI agents and their sandbox environments.

3. mcp/ (The Python Backend)

The original VibeServe MCP Server. This is a production-grade FastMCP server containing 28 specialized tools, SQLite-backed memory, multi-LLM routing with auto-fallback (OpenAI, DeepSeek, OpenRouter, Local Ollama), and direct integration endpoints.

Quickstart

One-Command Startup

# Clone and start everything
git clone https://github.com/ncsound919/VibeServe
cd VibeServe/ide
npm start

This starts:

  • The Vite dev server (port 3000)
  • The Hono API server (port 3002)
  • WebSocket connections for real-time agent streaming

Prerequisites

  • Node.js 20+
  • Python 3.10+
  • pnpm (for the orchestrator)

Setup the Entire Ecosystem

  1. Clone the monorepo:

    git clone https://github.com/ncsound919/VibeServe
    cd VibeServe
    
  2. Start the MCP Server:

    cd mcp
    pip install -e ".[dev]"
    cp .env.example .env
    # Start in dev mode or hook into Claude Desktop
    pytest tests/ -v
    
  3. Start the Orchestrator:

    cd ../orchestrator
    pnpm install
    pnpm run build
    pnpm run dev
    
  4. Start the IDE:

    cd ../ide
    npm install
    npm run dev
    

The system will now be fully interconnected.


Architecture

VibeServe IDE (React / Vite)
       ↓ WebSocket / REST
VibeServe Orchestrator (Node.js / Express)
       ↓ stdio MCP Protocol
VibeServe MCP Server (Python / FastMCP)
  ├── 28 Tools · 5 Resources · 6 Prompts
  ├── V5 Agentic Pipeline
  ├── LLMRouter (Auto-fallback chain)
  ├── MemoryStore (aiosqlite)
  └── SchemaValidator (WCAG AAA enforcement)


---

## License

MIT License. See [LICENSE](LICENSE) for details.

---

## Windows Bridge (TypeScript + Hono)

The `vibeserve/ts_bridge/` directory contains a **TypeScript-native Hono HTTP bridge** that
replaces the Python `http_bridge.py` on Windows, avoiding ProactorEventLoop issues with
asyncio servers. It spawns `python -m vibeserve` as a child process and communicates with
the Python MCP server via **stdin/stdout JSON-RPC** (the standard MCP stdio transport).

### Quick Start

```powershell
cd vibeserve\ts_bridge
npm install
.\start-bridge.ps1

Or with custom settings:

.\start-bridge.ps1 -Port 9000 -Python "python3.12" -Host "0.0.0.0"

Architecture

Client (HTTP / WebSocket)
       ↓
ts_bridge (Hono + TypeScript)
       ↓ stdin/stdout JSON-RPC
python -m vibeserve (FastMCP stdio server)

Endpoints

Method Path Description
GET /health Health check
POST /tools/list List available MCP tools
POST /tools/call Call an MCP tool by name
WS /ws WebSocket for streaming tool calls

WebSocket Protocol

Connect to ws://host:port/ws and send JSON messages:

{ "type": "tool_call", "name": "vs_memory_get", "arguments": { "workspace_id": "demo" } }
{ "type": "ping" }

Testing

cd vibeserve\ts_bridge
npm test

from github.com/ncsound919/VibeServe

Установить VibeServe в Claude Desktop, Claude Code, Cursor

Рекомендуется · одна команда, все IDE
unyly install vibeserve

Ставит в Claude Desktop, Claude Code, Cursor и VS Code — сам разбирается с npx, uvx и сборкой из исходников.

Впервые? Поставь CLI: curl -fsSL https://unyly.org/install | sh

Или настроить вручную

Выполни в терминале:

claude mcp add vibeserve -- uvx --from git+https://github.com/ncsound919/VibeServe vibeserve

FAQ

VibeServe MCP бесплатный?

Да, VibeServe MCP бесплатный — установка в пару кликов через Unyly без оплаты.

Нужен ли API-ключ для VibeServe?

Нет, VibeServe работает без API-ключей и переменных окружения.

VibeServe — hosted или self-hosted?

Self-hosted: сервер запускается локально на твоей машине командой из раздела установки.

Как установить VibeServe в Claude Desktop, Claude Code или Cursor?

Открой VibeServe на unyly.org, выбери вкладку своего клиента (Claude Desktop, Claude Code, Cursor) и нажми Install — конфиг сгенерируется автоматически, без правки JSON.

Похожие MCP

Compare VibeServe with

Не уверен что выбрать?

Найди свой стек за 60 секунд

Автор?

Embed-бейдж для README

Похожее

Все в категории development