TwinCat-MCP
MCP server for TwinCAT 3 PLC development enabling AI coding agents to build, configure, deploy, and debug TwinCAT PLC projects through a standard tool interface.
README
TwinCat-MCP โ Documentation
Source for the public user documentation of TwinCat-MCP โ an MCP server for TwinCAT 3 PLC development that lets AI coding agents (Claude Code, GitHub Copilot CLI, Cursor) build, configure, deploy, and debug TwinCAT PLC projects through a standard tool interface.
๐ Live site: docs.twincatmcp.qubernetic.com
Built with MkDocs Material. This repository holds the documentation content only; the product itself lives in a separate private repository.
Local development
Requires Python 3.x. Use a virtual environment to match the pinned build:
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install -r requirements.txt
mkdocs serve # live preview at http://127.0.0.1:8000
mkdocs build --strict # production build (must pass โ CI gate)
The social-card plugin needs the Cairo graphics libraries. On Debian/Ubuntu:
sudo apt-get install libcairo2-dev libfreetype6-dev libffi-dev libjpeg-dev libpng-dev libz-dev
Repository layout
mkdocs.yml # site config: theme, nav, plugins, brand
requirements.txt # pinned mkdocs-material + plugins
docs/
โโโ index.md # landing / showcase
โโโ CNAME # custom domain (docs.twincatmcp.qubernetic.com)
โโโ assets/ # logo (light/dark), favicon
โโโ stylesheets/extra.css # brand accent + dark-mode logo swap
โโโ getting-started/ # installation, agent connection, configuration
โโโ licensing/ # user-facing licensing how-to
โโโ tools/overview.md # tools overview
โโโ changelog.md # public changelog
.github/workflows/deploy-docs.yml # build + deploy to GitHub Pages
SECURITY.md ยท CODE_OF_CONDUCT.md ยท LICENSE
How it deploys
Every push to main runs the deploy workflow:
it builds the site with mkdocs gh-deploy --force (strict mode) and publishes to
the gh-pages branch, which GitHub Pages serves at the custom domain. The
docs/CNAME file preserves docs.twincatmcp.qubernetic.com across deploys.
Contributing
- Branching: Gitflow โ work on
feature/*, PR intodevelop;mainis the published site. - Commits: Conventional Commits (
docs:,feat:,fix:,chore:, โฆ). - Keep
mkdocs build --strictgreen โ broken links and nav fail the build (and the deploy).
โ ๏ธ This is a public repository
Only curated, user-facing content belongs here. Never add:
- how licensing is enforced under the hood (token issuance/validation, machine binding, replay protection);
- TwinCAT Automation-Interface implementation details or internal type names;
- internal source, samples, or planning documents;
- the name of any prior employer or third party.
When in doubt, leave it out โ this content is world-readable.
License
ยฉ 2026 Csaba Birรณ (Qubernetic). All rights reserved. See LICENSE. Documentation is published for use with the TwinCat-MCP product; redistribution or derivative works require permission.
<sub>A <a href="https://qubernetic.com">Qubernetic</a> product โ we build the future.</sub>
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.