WinCC Unified MCP XT
An MCP server that interfaces with SIEMENS WinCC Unified SCADA systems via GraphQL to manage real-time and historical tag data. It enables AI assistants to browse SCADA objects, read or write tag values, and perform alarm management tasks such as fetching, acknowledging, and resetting alarms.
README
WinCC Unified MCP XT
A Model Context Protocol (MCP) server designed to interface with SIEMENS WinCC Unified SCADA systems via their GraphQL API. This server exposes various WinCC Unified functionalities as MCP tools, enabling AI assistants and other MCP-compatible clients to interact programmatically with the SCADA system.
This project is based on the repository by Andreas Vogler
🔧 Features
- Connects to a WinCC Unified GraphQL endpoint.
- Provides MCP tools for:
- ✅ User authentication (
login-user) - 📂 Browsing SCADA objects (
browse-objects) - 📊 Reading current tag values (
get-tag-values) - 🕒 Querying historical/logged tag data (
get-logged-tag-values) - 🚨 Fetching active alarms (
get-active-alarms) - 📁 Fetching logged alarms (
get-logged-alarms) - ✍️ Writing values to tags (
write-tag-values) - 🟢 Acknowledging alarms (
acknowledge-alarms) - 🔄 Resetting alarms (
reset-alarms)
- ✅ User authentication (
- Optional automatic service account login with token refresh mechanism.
⚙️ Prerequisites
- Node.js (v18.x or newer recommended)
- npm (comes with Node.js)
- Access to a running WinCC Unified GraphQL server endpoint
⚙️ Configuration
this server uses a config.js file written in ES module syntax.
config.js (ESM) example:
export const config = {
URL: "https://your-wincc-server.example.com/graphql", // required
userName: "service_account_username", // optional
pwr: "service_account_password", // optional
};
🚀 How to Start
- Navigate to the project folder:
cd your-project-directory
- Install dependencies:
npm install
-
Edit config.js as shown above.
-
Start the server
node start
🖥️ Connecting with Claude Desktop
To use this MCP server with Claude AI (desktop version):
-
Find or create the claude_desktop_config.json file (typically in the Claude app config folder).
-
Add or update the following:
{
"mcpServers": {
"WinCC Unified": {
"command": "npx",
"args": ["mcp-remote", "http://localhost:3000/mcp"]
}
}
}
- Ensure @modelcontextprotocol/tools is installed:
npm install -g @modelcontextprotocol/tools
🧰 Available MCP Tools
| Tool | Description |
|---|---|
login-user |
Logs in with username/password. |
browse-objects |
Browses configured SCADA elements. |
get-tag-values |
Retrieves live tag values. |
get-logged-tag-values |
Gets historical tag data. |
get-active-alarms |
Lists currently active alarms. |
get-logged-alarms |
Shows previously triggered alarms. |
write-tag-values |
Updates one or more tags. |
acknowledge-alarms |
Acknowledges alarms. |
reset-alarms |
Resets alarms. |
📝 Notes
-
If configured, a service account is automatically logged in and token refreshed every minute.
-
A user's manual login overrides the service session temporarily.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。