WinCC Unified MCP XT
An MCP server for interfacing with SIEMENS WinCC Unified SCADA systems via their GraphQL API.
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.
関連サーバー
Scout Monitoring MCP
スポンサーPut performance and error data directly in the hands of your AI assistant.
Alpha Vantage MCP Server
スポンサーAccess financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
MCP Aggregator
A universal aggregator that combines multiple MCP servers into a single endpoint.
MCP迭代管理工具
An iteration management tool to automate the collection and submission of iteration information to a CodeReview system.
MCP Server Boilerplate
A TypeScript boilerplate for building MCP servers with streamable HTTP and OAuth proxy support.
Postman Agent Generator
An MCP server generated by Postman Agent Generator for automated API tools.
Abstract MCP Server
Caches large tool responses to files and returns compact resource links to save LLM context window space.
Authless MCP Server
A template for creating a remote, authentication-free MCP server deployable on Cloudflare Workers.
PipeCD
Integrate with PipeCD to manage applications and deployments.
CodeRabbit
Interact with CodeRabbit AI reviews on GitHub pull requests.
repomemory
Persistent, structured memory for AI coding agents. Your repo never forgets.
ndlovu-code-reviewer
Manual code reviews are time-consuming and often miss the opportunity to combine static analysis with contextual, human-friendly feedback. This project was created to experiment with MCP tooling that gives AI assistants access to a purpose-built reviewer. Uses the Gemini cli application to process the reviews at this time and linting only for typescript/javascript apps at the moment. Will add API based calls to LLM's in the future and expand linting abilities. It's also cheaper than using coderabbit ;)