Synology NAS 기기용 모델 컨텍스트 프로토콜(MCP) 서버입니다. AI 어시스턴트가 안전한 인증 및 세션 관리를 통해 파일 및 다운로드를 관리할 수 있도록 합니다.

** 🌟 신규: 통합 서버가 Claude/커서(stdio)와 샤오즈(WebSocket)를 동시에 지원합니다!**

📦 PyPI에서 설치

저장소를 복제할 필요는 없고 — PyPI에서 바로 패키지를 설치하세요:

이 명령어는 두 개의 동등한 명령어를 설치합니다: synology-mcp와 mcp-server-synology.

MCP 클라이언트의 경우, uvx가 가장 간단한 선택입니다 — 패키지를 자동으로 다운로드하고 캐시하여 수동 설치나 로컬 클론이 필요하지 않습니다:

구성은 패키지 외부에 위치하므로 소스 체크아웃과 동일하게 작동합니다: 구성 옵션에 설명된 대로 ~/.config/synology-mcp/settings.json를 생성합니다.

🚀 도커로 빠른 시작

1️# ¶ 설정 환경

2️^ .env 파일 구성

기본 구성 (Claude/커서만):

확장 구성(클로드/커서 + 샤오즈) 모두:

.env는 실행 시에 읽히며, 이미지에 베이크되지 않습니다 — docker-compose.yml env_file를 통해 컨테이너 환경 변수로 항목을 주입하므로, 파일 자체는 컨테이너 안에 존재하지 않습니다. 선택 사항입니다: 만약

💾 Synology MCP Server

A Model Context Protocol (MCP) server for Synology NAS devices. Enables AI assistants to manage files and downloads through secure authentication and session management.

🌟 NEW: Unified server supports both Claude/Cursor (stdio) and Xiaozhi (WebSocket) simultaneously!

📦 Install from PyPI

No need to clone the repository — install the package directly from PyPI:

# With pip
pip install mcp-server-synology

# Or with pipx (isolated environment)
pipx install mcp-server-synology

# Or with uv
uv tool install mcp-server-synology

This installs two equivalent commands: synology-mcp and mcp-server-synology.

For MCP clients, uvx is the simplest option — it downloads and caches the package automatically, no manual install or local clone required:

{
  "mcpServers": {
    "synology": {
      "command": "uvx",
      "args": ["mcp-server-synology"]
    }
  }
}

Configuration lives outside the package, so it works the same as a source checkout: create ~/.config/synology-mcp/settings.json as described in Configuration Options.

🚀 Quick Start with Docker

1️⃣ Setup Environment

# Clone repository
git clone https://github.com/atom2ueki/mcp-server-synology.git
cd mcp-server-synology

# Create environment file
cp env.example .env

2️⃣ Configure .env File

Basic Configuration (Claude/Cursor only):

# Required: Synology NAS connection
SYNOLOGY_URL=http://192.168.1.100:5000
SYNOLOGY_USERNAME=your_username
SYNOLOGY_PASSWORD=your_password

# Optional: Auto-login on startup
AUTO_LOGIN=true
VERIFY_SSL=false

Extended Configuration (Both Claude/Cursor + Xiaozhi):

# Required: Synology NAS connection
SYNOLOGY_URL=http://192.168.1.100:5000
SYNOLOGY_USERNAME=your_username
SYNOLOGY_PASSWORD=your_password

# Optional: Auto-login on startup
AUTO_LOGIN=true
VERIFY_SSL=false

# Enable Xiaozhi support
ENABLE_XIAOZHI=true
XIAOZHI_TOKEN=your_xiaozhi_token_here
XIAOZHI_MCP_ENDPOINT=wss://api.xiaozhi.me/mcp/

.env is read at run time, never baked into the image — docker-compose.yml injects its entries as container environment variables via env_file, so the file itself is not present inside the container. It is optional: if you configure NASes with settings.json instead (recommended), you can skip this file entirely.

3️⃣ Run with Docker

One simple command supports both modes:

# Claude/Cursor only mode (default if ENABLE_XIAOZHI not set)
docker-compose up -d

# Both Claude/Cursor + Xiaozhi mode (if ENABLE_XIAOZHI=true in .env)
docker-compose up -d

# Build and run
docker-compose up -d --build

4️⃣ Alternative: Local Python

# Install the package and its dependencies (from PyPI, or from a clone with 'pip install .')
pip install mcp-server-synology

# Run with environment control
python main.py

🔌 Client Setup