nickol-knx-mcp

nickol-knx-mcp

Reads .knxproj files, analyzes group addresses/DPTs/topology, generates Home Assistant KNX YAML and ETS-importable group-address files (XML/CSV), and produces human-readable reports without touching the live KNX bus.

Category
Visit Server

README

nickol-knx-mcp

A design-time KNX / ETS6 assistant exposed as an MCP server.

It reads your .knxproj, analyzes group addresses / DPTs / topology, generates Home Assistant KNX YAML and ETS-importable group-address files (XML/CSV), and produces human-readable reports β€” without ever touching the live KNX bus.

CI License: MIT Python 3.10+ Status: beta Live demo Join the discussion

πŸ‡·πŸ‡Ί Русская вСрсия: README.ru.md


<p align="center"> <a href="https://nickoscope.github.io/nickol-knx-mcp/"> <img src="docs/assets/banner.svg" alt="nickol-knx-mcp β€” live interactive demo and dashboard" width="100%"> </a> </p>

<h3 align="center">🎬 <a href="https://nickoscope.github.io/nickol-knx-mcp/">Explore the live interactive demo & dashboardΒ β†’</a></h3>

New β€” a whole demo house. examples/demo-home ships a synthetic 239-GA / 47-Function project, the tool's generated report + Home Assistant config + ETS export, and a full smart-home β€œbrain” β€” circadian lighting, an 8-factor climate setpoint, a presence/season/time state machine and statistics β€” driving a 5-view dashboard. See it all on the live siteΒ β†—.


πŸ–₯️ The dashboard β€” live in Home Assistant

Real screenshots from a live Home Assistant running the demo house. Note the brain at work: Summer flipped the whole house to Cooling at 92 % comfort, lights follow a circadian curve (71 % @ 3750 K), and the climate setpoints are computed, not set by hand.

<p align="center"> <img src="docs/assets/screenshots/overview.png" alt="Overview β€” home mode, comfort gauge, scenes, climate snapshot" width="78%"> </p>

Climate Lighting
<img src="docs/assets/screenshots/climate.png" alt="Climate view" width="100%"> <img src="docs/assets/screenshots/lighting.png" alt="Lighting view" width="100%">
Energy & stats Presence
<img src="docs/assets/screenshots/energy.png" alt="Energy view" width="100%"> <img src="docs/assets/screenshots/presence.png" alt="Presence view" width="100%">

β–Ά Explore it interactively on the live site β†’ Β· config in examples/demo-home/ha-brain


πŸ§ͺ Status & call for testers

This is a public beta. The full pipeline passes an end-to-end smoke test on a synthetic 16-group-address project, but it has had limited testing against real-world .knxproj files β€” and real ETS projects are wonderfully messy and diverse.

πŸ‘‰ If you have an ETS5/ETS6 project, please try it and tell us what happens. Open a Real-project test report issue. The tool is read-only and never connects to a bus, so testing is safe (see Safety model). See CONTRIBUTING.md for details.

πŸ’¬ Join the discussion β†’ β€” say hi, ask anything, or share what the tool found on your project.


Why this exists

As of mid-2026 there is no off-the-shelf ETS6 ↔ Claude / MCP tool. The KNX community has been explicitly asking for an integration that can inspect and help modify projects (adding / renaming devices and group addresses) through an AI/CLI workflow. This package fills exactly the design-time layer β€” the missing one.

The recommended full setup is four layers; only one needs to be built from scratch:

Layer Purpose What to use Build it?
1. Live states, control, debugging a running house official Home Assistant MCP Server + KNX (XKNX) integration No, already exists
2. Design-time parse .knxproj, validate DPT/naming/status, generate HA YAML & ETS XML/CSV nickol-knx-mcp (this package) YES β€” this is the gap
3. Files + Git YAML/CSV/XML, versioning the address schema standard filesystem + git MCP servers No, already exists
4. Skill design rules (GA structure, naming, DPT, scenes) CLAUDE.md in this package No, included

Safety by design: layer 2 (this server) physically cannot connect to a bus. It has no network/bus dependency at all β€” it only reads .knxproj and writes files into a confined workspace. The "never write to a live bus" requirement is enforced structurally, not by promise. Any real interaction with the house goes only through layer 1 (Home Assistant).


What the server does

  • Parses password-protected ETS5/ETS6 .knxproj files via xknxproject (3.9.x).
  • Extracts group addresses, DPTs, devices, topology, descriptions, and ETS Functions.
  • Classifies every GA: category (lighting / shutter / hvac / sensor / scene / energy / diagnostics) and kind (command / status / sensor) β€” from the DPT plus multilingual (EN/DE/RU) keywords in the name.
  • Validates naming against a 3-level structure and a configurable regex.
  • Finds missing status addresses β€” primarily from ETS Function roles, falling back to name-token pairing (command in …/0/…, feedback in …/4/… is common, so it matches by name tokens rather than by middle-group adjacency).
  • Catches DPT problems: missing DPT, mismatch between a Communication Object and its GA, and the same logical name carrying different DPTs.
  • Generates Home Assistant KNX YAML β€” category by category, conservatively: covers β†’ lights β†’ switches β†’ sensors/binary. Ambiguous items (e.g. DPT 5.001 β€” brightness vs blind position) are not guessed; they go into a review list instead.
  • Generates ETS-importable group addresses in XML (the recommended knx.org/xml/ga-export/01 schema) and CSV (ETS's native layout).
  • Writes a Markdown report (inventory + πŸ”΄πŸŸ‘πŸ”΅ findings + HA-mapping preview + next steps) for human review before any import.

All writes go only into the workspace directory (NICKOL_KNX_WORKSPACE, default ./knx-workspace); writes outside it are rejected.


Installation

Requires Python 3.10+.

git clone https://github.com/NickoScope/nickol-knx-mcp.git
cd nickol-knx-mcp
python3 -m venv .venv && source .venv/bin/activate
pip install -e .

Dependencies: mcp>=1.10, xknxproject>=3.8, PyYAML>=6.0.

On Debian/Ubuntu, if pip complains about an externally-managed environment, use a venv (as above) or pip install -e . --break-system-packages. If PyJWT conflicts, run pip install mcp --ignore-installed PyJWT first.

Verify:

python tests/test_pipeline.py     # synthetic 16-GA project, end-to-end smoke test
nickol-knx-mcp                    # start the MCP server (stdio)

Connecting to Claude

Claude Desktop

examples/claude_desktop_config.json wires up nickol-knx + filesystem + git + home-assistant. Minimal fragment (macOS config path: ~/Library/Application Support/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "nickol-knx": {
      "command": "nickol-knx-mcp",
      "env": { "NICKOL_KNX_WORKSPACE": "/path/to/your/knx-workspace" }
    }
  }
}

Claude Code

claude mcp add nickol-knx \
  -e NICKOL_KNX_WORKSPACE="$HOME/knx-workspace" \
  -- /absolute/path/to/.venv/bin/nickol-knx-mcp

Then drop CLAUDE.md into your project root β€” it acts as an ETS Assistant skill (design rules, safety rules, 3-level GA structure, command/status pairing, DPT discipline, naming, KNX Secure keyring handling, and the recommended workflow).


MCP tools (12)

Tool Purpose
load_project(path, password?, language?) parse a .knxproj (read-only) and cache it
list_group_addresses(category?, kind?) list GAs with classification and filters
get_devices() devices + their communication objects
get_topology() topology (areas / lines / devices)
check_naming(name_regex?) validate naming / structure
check_missing_status() actuators lacking a status object
check_dpt() missing / inconsistent DPTs
analyze_all(name_regex?) run every check at once
generate_ha_package(output_path?) HA KNX YAML + review list
generate_ets_group_addresses(fmt="xml"|"csv", output_path?) ETS-importable GAs
project_report(output_path?, name_regex?) Markdown report
workspace_info() workspace path + safety guarantees

Typical workflow

  1. load_project β†’ point it at your .knxproj (+ password if protected).
  2. analyze_all or project_report β†’ read the findings; human review first.
  3. Fix naming/DPT/status in ETS (by importing generated GAs or manually).
  4. generate_ets_group_addresses(fmt="xml") β†’ import the missing GAs into ETS.
  5. generate_ha_package β†’ place the YAML into Home Assistant; resolve review items by hand.
  6. Keep everything (.knxproj export, HA configs, address schema) in Git.
  7. Touch the live house only through the Home Assistant MCP (layer 1).

Limitations (honest)

  • command/status and category classification is a heuristic (DPT + names + ETS Functions). On messy projects with no Functions and non-standard names, false negatives/positives are possible β€” which is why the report is always for human review, and ambiguity goes to review, not into config.
  • DPT 5.001 is structurally ambiguous (brightness vs position); it's disambiguated by keywords β€” double-check with non-standard naming.
  • The HA generator is conservative: it would rather defer an item to review than emit a wrong entity.
  • The server never writes to the bus and never talks to ETS directly β€” ETS exchange is file import/export of GAs only.
  • Tested only on a synthetic project so far. Real .knxproj files vary a lot β€” hence the call for testers.

πŸ”’ Safety model

  • No bus access, structurally. There is no networking or bus library in the dependency tree. workspace_info() reports bus_access: false.
  • Read-only on your project. project.py is the only module that touches .knxproj, and it only reads.
  • Confined writes. All output is constrained to NICKOL_KNX_WORKSPACE; paths outside it are rejected.
  • Human-in-the-loop. Generate a project_report and review it before importing into ETS or deploying into Home Assistant.

Found a security issue? See SECURITY.md.


Package layout

nickol-knx-mcp/
β”œβ”€β”€ nickol_knx_mcp/
β”‚   β”œβ”€β”€ dpt_map.py        # DPT β†’ category / kind / HA platform / value_type
β”‚   β”œβ”€β”€ project.py        # the ONLY module that reads .knxproj (read-only)
β”‚   β”œβ”€β”€ pairing.py        # command↔status pairing by name tokens
β”‚   β”œβ”€β”€ analyze.py        # naming / missing-status / DPT checks
β”‚   β”œβ”€β”€ generate_ha.py    # Home Assistant KNX YAML generation
β”‚   β”œβ”€β”€ generate_ets.py   # ETS XML + CSV generation
β”‚   β”œβ”€β”€ report.py         # Markdown report
β”‚   └── server.py         # FastMCP server, 12 tools, confined writes
β”œβ”€β”€ tests/test_pipeline.py
β”œβ”€β”€ examples/claude_desktop_config.json
β”œβ”€β”€ CLAUDE.md             # ETS Assistant skill / playbook
β”œβ”€β”€ pyproject.toml
└── README.md

Contributing

Testers and contributors are very welcome β€” especially real-project test reports. See CONTRIBUTING.md and the issue templates.

License

MIT Β© 2026 Nikolay Miroshnichenko

Not affiliated with or endorsed by the KNX Association. "KNX" and "ETS" are trademarks of the KNX Association cc. This is an independent, community tool.

Recommended Servers

playwright-mcp

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.

Official
Featured
TypeScript
Magic Component Platform (MCP)

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.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

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.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

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.

Official
Featured
TypeScript
Kagi MCP Server

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.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

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.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured