经 AI Skill Hub 精选评估,synology MCP 工具 获评「强烈推荐」。这款MCP工具在功能完整性、社区活跃度和易用性方面表现出色,AI 评分 8.2 分,适合有一定技术背景的用户使用。
为群晖NAS设计的Model Context Protocol服务器,能让AI助手直接访问和控制NAS存储、文件系统等功能。支持Python开发,适合需要智能化管理NAS存储的开发者和企业用户。
synology MCP 工具 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
为群晖NAS设计的Model Context Protocol服务器,能让AI助手直接访问和控制NAS存储、文件系统等功能。支持Python开发,适合需要智能化管理NAS存储的开发者和企业用户。
synology MCP 工具 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
# 方式一:通过 Claude Code CLI 一键安装
claude skill install https://github.com/atom2ueki/mcp-server-synology
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"synology-mcp---": {
"command": "npx",
"args": ["-y", "mcp-server-synology"]
}
}
}
# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
# 安装后在 Claude 对话中直接使用 # 示例: 用户: 请帮我用 synology MCP 工具 执行以下任务... Claude: [自动调用 synology MCP 工具 MCP 工具处理请求] # 查看可用工具列表 # 在 Claude 中输入:"列出所有可用的 MCP 工具"
// claude_desktop_config.json 配置示例
{
"mcpServers": {
"synology_mcp___": {
"command": "npx",
"args": ["-y", "mcp-server-synology"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效

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!
main.py supports both stdio and WebSocket clientsENABLE_XIAOZHI environment variablepip install -r requirements.txt
```bash
One simple command supports both modes:
```bash
docker-compose up -d --build ```
By default the server speaks stdio, which means the MCP client has to spawn the process locally (or via a bridge such as SSH/docker exec). For setups where the NAS is remote (different machine from where Claude/Cursor runs), you can expose the MCP server over HTTP/SSE using mcp-proxy. This makes it consumable by any MCP client that supports URL-based connectors — exactly like ha-mcp or other "remote" MCP servers.
1. mcp-proxy is installed automatically when you build the HTTP image — it lives in requirements-http.txt and the provided compose file sets the INSTALL_HTTP=true build arg (it is not in the default stdio/Xiaozhi image). 2. Use the provided docker-compose.http.yml:
```bash
docker compose -f docker-compose.http.yml up -d --build docker logs -f synology-mcp-http ```
You should see mcp-proxy report Uvicorn running on http://0.0.0.0:8765 and the auto-login succeed.
1. Add to your .env file:
ENABLE_XIAOZHI=true
XIAOZHI_TOKEN=your_xiaozhi_token_here
2. Run normally: ```bash
cp env.example .env ```
Basic Configuration (Claude/Cursor only): ```bash
AUTO_LOGIN=true VERIFY_SSL=false
**Extended Configuration (Both Claude/Cursor + Xiaozhi):**bash
AUTO_LOGIN=true VERIFY_SSL=false
docker-compose up -d
python main.py ```
In Claude Desktop (or any MCP client that supports remote connectors), add a custom connector pointing at:
https://synology-mcp.example.com/sse
No command, no args, no local Python — just a URL.
python main.py
⚠️ Security Warning: Use a Dedicated Account For this MCP server, create a dedicated Synology user account with appropriate permissions. This account should: - NOT have 2FA enabled - The MCP server cannot handle 2FA prompts and will fail authentication - Have minimal required permissions only (not admin!) - Be used exclusively for MCP server automation Using your primary account with 2FA is dangerous - if auto-login fails, you may be locked out of your NAS!
| Variable | Required | Default | Description |
|---|---|---|---|
SYNOLOGY_URL | Yes* | - | NAS base URL (e.g., http://192.168.1.100:5000) |
SYNOLOGY_USERNAME | Yes* | - | Username for authentication |
SYNOLOGY_PASSWORD | Yes* | - | Password for authentication |
AUTO_LOGIN | No | true | Auto-login on server start |
VERIFY_SSL | No | false | Verify SSL certificates |
DEBUG | No | false | Enable debug logging |
ENABLE_XIAOZHI | No | false | Enable Xiaozhi WebSocket bridge |
XIAOZHI_TOKEN | Xiaozhi only | - | Authentication token for Xiaozhi |
XIAOZHI_MCP_ENDPOINT | No | wss://api.xiaozhi.me/mcp/ | Xiaozhi WebSocket endpoint |
*Required for auto-login and default operations
For managing multiple Synology NAS devices, use the XDG standard config directory (~/.config/synology-mcp/settings.json):
mkdir -p ~/.config/synology-mcp
touch ~/.config/synology-mcp/settings.json
chmod 600 ~/.config/synology-mcp/settings.json # Important: secure permissions!
Note: This follows the XDG Base Directory Specification - ~/.config/ is the standard location for user configuration files on Linux/macOS. You can customize the location by setting the XDG_CONFIG_HOME environment variable.
With Docker: The docker-compose.yml automatically mounts your ~/.config/synology-mcp directory into the container at /home/mcpuser/.config/synology-mcp, so multi-NAS works out of the box with Docker as well.
settings.json format:
{
"synology": {
"nas1": {
"host": "192.168.1.100",
"port": 5000,
"username": "admin",
"password": "your_password",
"note": "Primary NAS at home"
},
"nas2": {
"host": "192.168.1.200",
"port": 5001,
"username": "admin",
"password": "your_password",
"note": "Backup NAS"
}
},
"xiaozhi": {
"enabled": false,
"token": "your_xiaozhi_token",
"endpoint": "wss://api.xiaozhi.me/mcp/"
},
"server": {
"auto_login": true,
"verify_ssl": false,
"session_timeout": 3600,
"debug": false,
"log_level": "INFO"
}
}
Configuration fields: <div class="rdm-tbl-wrap"><table class="rdm-tbl"><thead><tr><th>Field</th><th>Required</th><th>Description</th></tr></thead><tbody><tr><td>host</td><td>Yes</td><td>NAS hostname or IP address</td></tr><tr><td>port</td><td>No</td><td>API port (default: 5000 for HTTP, 5001 for HTTPS)</td></tr><tr><td>username</td><td>Yes</td><td>NAS username</td></tr><tr><td>password</td><td>Yes</td><td>NAS password</td></tr><tr><td>note</td><td>No</td><td>Optional description for your reference</td></tr></tbody></table></div>
Notes: - The server will use port 5001 (HTTPS) if port is 5001, otherwise defaults to HTTP (5000) - File permissions: chmod 600 ~/.config/synology-mcp/settings.json is required for security - The server will refuse to load settings if permissions are too open - Both .env and settings.json can be used together (settings.json takes priority)
New unified architecture supports both clients simultaneously!
```bash
Add to your Continue configuration (.continue/config.json):
{
"mcpServers": {
"synology": {
"command": "docker-compose",
"args": [
"-f", "/path/to/your/mcp-server-synology/docker-compose.yml",
"run", "--rm", "synology-mcp"
],
"cwd": "/path/to/your/mcp-server-synology"
}
}
}
If you prefer not to use Docker:
{
"mcpServers": {
"synology": {
"command": "python",
"args": ["main.py"],
"cwd": "/path/to/your/mcp-server-synology",
"env": {
"SYNOLOGY_URL": "http://192.168.1.100:5000",
"SYNOLOGY_USERNAME": "your_username",
"SYNOLOGY_PASSWORD": "your_password",
"AUTO_LOGIN": "true",
"ENABLE_XIAOZHI": "false"
}
}
}
}
Synology MCP 服务器是一个 Model Context Protocol (MCP) 服务器,专为 Synology NAS 设备设计。它通过安全的身份验证和会话管理使 AI 助手能够管理文件和下载。
本项目的关键功能包括:零配置冲突、并行操作、所有工具可用、向后兼容、自动重连和环境控制。
本项目需要以下环境依赖和系统要求:
快速开始使用 Docker:
工作流 / 模块说明:本项目采用新一代的统一架构,支持同时访问 Claude/Cursor 和 Xiaozhi 客户端。
优质的MCP生态工具,填补AI与NAS集成空白。代码活跃度好,文档完整,适合企业级应用。
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ MIT 协议 — 最宽松的开源协议之一,可自由商用、修改、分发,仅需保留版权声明。
AI Skill Hub 点评:synology MCP 工具 的核心功能完整,质量优秀。对于Claude Desktop / Claude Code 用户来说,这是一个值得纳入个人工具库的选择。建议先在非生产环境试用,再逐步推广。
| 原始名称 | mcp-server-synology |
| 原始描述 | 开源MCP工具:💾 Model Context Protocol (MCP) server for Synology NAS - Enables AI assistants 。⭐98 · Python |
| Topics | NAS管理MCP协议群晖存储自动化AI集成 |
| GitHub | https://github.com/atom2ueki/mcp-server-synology |
| License | MIT |
| 语言 | Python |
收录时间:2026-05-16 · 更新时间:2026-05-19 · License:MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端