OpenTIA-MCP
Allows interaction with Siemens TIA Portal via its Openness API, enabling AI agents to manage PLC projects, blocks, HMI tags, diagnostics, simulation, download to PLC, and documentation generation.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@OpenTIA-MCPopen the project 'Conveyor' and compile it"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
OpenTIA-MCP
An MCP (Model Context Protocol) server that lets AI agents interact with Siemens TIA Portal via its Openness API.
Requirements
Windows (TIA Portal is Windows-only)
Python 3.11+
TIA Portal V17–V20 with Openness API installed (V20 is what this repo is verified against)
pip (Python package installer)
For simulation and automated downloads: S7-PLCSIM Advanced (verified with 7.0)
Related MCP server: T-IA Connect (Siemens TIA Portal)
Installation
# Create a virtual environment (recommended)
python -m venv .venv
.venv\Scripts\activate
# Install the package in editable mode
pip install -e .Configuration
Copy or create an opentia.toml file (see opentia.toml for the template).
The server searches for it in this order:
Path specified by the
OPENTIA_CONFIGenvironment variable./opentia.tomlin the current working directory%APPDATA%\opentia-mcp\opentia.toml
Usage
# Start the MCP server
python -m opentia_mcpOr use the installed entry point:
opentia-mcpTools
Tool | Purpose |
| Attach to a running Portal (use |
| Project lifecycle (Multiuser local sessions are handled: saving goes through |
| Block inventory and SCL round-trip |
| Create blocks from SCL (optionally into a block group via |
| PLCSIM Advanced instance lifecycle (runtime API, not Openness) |
| Download to a virtual PLCSIM target and offline/online comparison |
| Project documentation |
Project Structure
src/opentia_mcp/
├── __init__.py
├── __main__.py # Entry point
├── server.py # MCP server and tool registration
├── models.py # Pydantic models
├── errors.py # Exception hierarchy
├── config.py # Configuration loading
├── logging.py # Logging to stderr
└── tia/ # Openness API abstraction layer
├── __init__.py
├── portal.py # Connection lifecycle
├── project.py # Project management
├── block.py # PLC block CRUD
├── compilation.py # Compilation
├── reference.py # Cross-references
├── hmi.py # HMI tags
├── watch.py # Watch tables
├── diagnostic.py # Diagnostics
├── simulation.py # PLCSIM Advanced
├── download.py # Download to PLC
└── documentation.py # Documentation generationThis server cannot be deployed
Maintenance
Related MCP Connectors
MCP server enabling AI agents to manage Bitrix24 features via standardized protocol
MCP server for AI agents to plan, verify, and deploy Cloudflare-native apps.
MCP server for building and testing AI agents with multi-model experimentation and insights.
- ZapierOAuthcom.zapier
Hosted MCP server connecting AI assistants to 9,000+ apps and 40,000+ actions via Zapier.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceAn 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.8-
- AlicenseNot gradedqualityDmaintenanceIndustrial-grade MCP server for Siemens TIA Portal (V17–V21). 120+ tools for PLC programming: create blocks (FB/FC/OB/DB), manage tags, compile, download, and simulate with PLCSim Advanced. On-premise, sovereign-AI compatible.18MIT
- AlicenseAqualityAmaintenanceAn MCP server that gives AI agents access to the full Cumulocity API surface through a compact code-mode interface.3177 npm6MIT
- FlicenseNot gradedqualityAmaintenanceMCP server that connects AI assistants to Siemens TIA Portal via the Openness API. AI-assisted PLC programming, project management, hardware configuration, cross-reference analysis, and deployment. 19 tools, 230 actions.37-