広告掲載
MCP.so
ログイン

Synology MCP Server

@atom2ueki

リポジトリ

基本情報

カテゴリ

開発者ツール

ライセンス

MIT

トランスポート

stdio

作者

atom2ueki

Synology MCP Server について

💾 Model Context Protocol (MCP) server for Synology NAS - Enables AI assistants (Claude, Cursor, Continue) to manage files, downloads, and system operations through secure API integration. Features Docker deployment, auto-authentication, and comprehensive file system tools.

#mcp#synology#mcp-server

Synology MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "mcp-server-synology": {
      "command": "python",
      "args": [
        "main.py"
      ]
    }
  }
}

Synology MCP Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Synology MCP Server?

A Model Context Protocol (MCP) server for Synology NAS devices. It enables AI assistants like Claude and Cursor to manage files, downloads, and system health through secure authentication and session management. The unified server supports both Claude/Cursor (stdio) and Xiaozhi (WebSocket) simultaneously.

How to use Synology MCP Server?

Clone the repository, copy env.example to .env, and configure the Synology NAS URL, username, and password. Run with docker-compose up -d (or python main.py for local execution). Then add the server to your MCP client (Claude Desktop, Cursor, Continue, or Codeium) using the provided JSON configuration. For remote access, deploy with the HTTP/SSE image and front with a TLS-terminating reverse proxy.

Key features of Synology MCP Server

  • Unified server supports both stdio and WebSocket clients simultaneously
  • File system operations: list, search, create, delete, rename, move
  • Download Station management: create, pause, resume, delete tasks
  • Health monitoring: system info, utilization, disk health, volumes, network, UPS
  • Container Manager: list, get, start, stop containers

Use cases of Synology MCP Server

  • AI assistant to browse, upload, and organize files on a Synology NAS
  • Automate download tasks via Download Station using URLs or magnet links
  • Monitor NAS health (CPU, memory, disk SMART, UPS status) from a chat interface
  • Deploy a remote MCP endpoint so Claude/Cursor can access the NAS over the internet

よくある質問

1

What dependencies are required to run the server?

Docker is the primary method; alternatively, Python 3 with the packages in `requirements.txt`. The HTTP/SSE deployment also installs `mcp-proxy`.

2

How do I make the server accessible remotely?

Use the provided `docker-compose.http.yml` file to expose the MCP server over HTTP/SSE on port 8765, then front it with a reverse proxy (DSM Login Portal, Nginx, etc.) for TLS termination and optional authentication.

3

Does the server support multiple client protocols simultaneously?

Yes. When `ENABLE_XIAOZHI=true` is set in `.env`, the server acts as a bridge serving both stdio (for Claude/Cursor) and WebSocket (for Xiaozhi) at the same time.

4

What authentication is used?

The server authenticates with the Synology NAS using the credentials stored in the `.env` file (`SYNOLOGY_USERNAME`, `SYNOLOGY_PASSWORD`). The HTTP/SSE endpoint itself has no built-in authentication; it should be secured at the reverse proxy level.

5

Can I use this server with Continue (VS Code extension)?

Yes. Add the same Docker (or Python) configuration as for Claude/Cursor to your `./continue/config.json` `mcpServers` block.

コメント

「開発者ツール」の他のコンテンツ

Mcp-Warden

ermoluk

Local-first credential broker for MCP. AI coding agents (Claude Code, Cursor, Codex…) call APIs, SSH and databases through scoped presets; secrets stay in your OS keychain and never enter the agent's context.

4

Nebelus

Nebelus

Nebelus is an enterprise agentic-AI platform for regulated industries. This MCP server exposes the Nebelus Construction API: ~48 tools that give an MCP client full agent build parity — create/update/probe agents, edit ag

MCP Server By TestMu AI

TestMu AI

TestMu AI MCP Server lets developers run, debug, and triage tests through natural language directly from their IDE (Cursor, Claude, GitHub Copilot, and other MCP clients). It exposes five tools — HyperExecute (test orche

LastPing

LastPing

Know when your AI agents, cron jobs and CI pipelines fail, stall or go quiet. Your agent sets up monitors from a plain description, tells you what is broken and why, reads run history and traces, and writes notes on inci

SSH MCP Server

hypnosis

SSH MCP server for AI agents: remote commands, file transfer, log search and server audits through OpenSSH.

1
広告掲載