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 "Install 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-MCP open 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.
An MCP (Model Context Protocol) server that lets AI agents interact with Siemens TIA Portal via its Openness API.
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)
# Create a virtual environment (recommended)
python -m venv .venv
.venv\Scripts\activate
# Install the package in editable mode
pip install -e .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_CONFIG environment variable
./opentia.toml in the current working directory
%APPDATA%\opentia-mcp\opentia.toml
# Start the MCP server
python -m opentia_mcpOr use the installed entry point:
opentia-mcpTool | 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 |
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 installed
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Self-hosted MCP gateway: turn any API, database or MCP server into AI connectors — no code.
MCP server for AI agents to plan, verify, and deploy Cloudflare-native apps.
MCP server for AI dialogue using various LLM models via AceDataCloud
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/omirko00/OpenTIA-MCP'
If you have feedback or need assistance with the MCP directory API, please join our Discord server