bulaofen0036-coder/TIA_Portal_Openness_MCP

Drive Siemens TIA Portal V20/V21 (STEP 7, WinCC Unified) from any MCP client — create projects, generate PLC & HMI, compile & diagnose. Prebuilt runtime, no Openness coding required.

What it solves

This project provides an interface between AI assistants and Siemens TIA Portal (V20/V21), allowing engineers to automate industrial automation tasks using natural language. It solves the difficulty of programmatically interacting with TIA Portal's complex, proprietary environment by exposing its functionality through the Model Context Protocol (MCP).

How it works

The project acts as an MCP server that translates natural language requests from AI clients (like Claude Desktop, Cursor, or VS Code) into specific tool calls for the TIA Portal Openness API. It can create projects, configure hardware, generate PLC code (Tag, UDT, DB, SCL, LAD), build WinCC Unified screens, and compile projects. It also includes a CLI (tia) that allows for declarative project generation via YAML/JSON specifications without requiring an MCP client.

Who it’s for

It is designed for industrial automation engineers and developers who use Siemens TIA Portal and want to leverage AI to speed up repetitive tasks, automate project scaffolding, or integrate version control (via a text-based mapping interface) into their PLC development workflow.

Highlights

  • Full Automation: Enables end-to-end project generation, from hardware configuration to HMI screen design, via natural language.
  • Version Control Integration: Maps binary TIA Portal projects to text-based files, allowing for Git-based diffing and version management.
  • Flexible Interface: Works as an MCP server for AI integration or as a standalone CLI for scriptable project generation.
  • Broad Compatibility: Supports TIA Portal V20 and V21 with automatic environment health checks and diagnostic tools.
  • Safety-Focused: Provides mechanisms for human-in-the-loop approval before executing write operations.

Related

  • Project
    billion-token-one-task/Deepgraph

    An autonomous research agent that harvests scientific literature, maps evidence into a graph, and runs experiments to find and verify checkable research conclusions.

  • Project
    MemTensor/MemOS-Cloud-OpenClaw-Plugin

    A lifecycle plugin for OpenClaw and related hosts that integrates MemOS Cloud to provide AI agents with persistent memory recall and message storage.

  • Project
    goruck/home-generative-agent

    A Home Assistant integration that turns your smart home into a conversational agent capable of writing automations, analyzing camera feeds, and performing security audits using local or cloud LLMs.

  • Project
    ok-helloworld/vibe-pentest

    An AI-powered penetration testing tool that uses a multi-agent architecture to simulate human security experts in discovering vulnerabilities in web apps and APIs.