mcp-server-zwave-js-ui

mcp-server-zwave-js-ui

An MCP server that connects to Z-Wave JS UI's WebSocket to expose controller, node, and configuration information as tools for AI assistants to manage Z-Wave networks.

Category
Visit Server

README

mcp-server-zwave-js-ui

PyPI Python versions CI License: MIT

An MCP server for managing a Z-Wave network through Z-Wave JS UI. It connects to the zwave-js-server WebSocket that Z-Wave JS UI exposes and surfaces the mesh — controller, nodes, values, and configuration parameters — as tools an MCP client (e.g. Claude) can call.

Status: early / read-only. This first release covers read-only introspection. Write control and administrative operations are on the roadmap — see Roadmap.

Quickstart

  1. In Z-Wave JS UI, make sure the Z-Wave JS Server WebSocket is enabled (Settings → Home Assistant → WS Server; default port 3000). See What it connects to.

  2. Add the server to Claude Code, pointing ZWAVE_JS_URL at that WebSocket. No manual install needed — uvx fetches and runs the published package:

    claude mcp add zwave-js-ui \
      --env ZWAVE_JS_URL=ws://<host>:3000 \
      -- uvx mcp-server-zwave-js-ui
    
  3. Ask Claude about your mesh — it calls the read-only tools to answer:

    "Which Z-Wave controller am I running, and how many nodes are on the network?"

    "List my Z-Wave nodes and flag any that are dead or asleep."

For other MCP clients, isolated installs, and configuration details, see the sections below.

What it connects to

Z-Wave JS UI runs two servers: the web UI (default port 8091) and the Z-Wave JS Server WebSocket (default port 3000) that Home Assistant and this MCP server talk to. Point ZWAVE_JS_URL at the WebSocket, not the UI.

Install

Requires Python 3.12+.

pip install mcp-server-zwave-js-ui
# or, isolated:
pipx install mcp-server-zwave-js-ui
# or, no install:
uvx mcp-server-zwave-js-ui

Configure

Variable Default Description
ZWAVE_JS_URL ws://localhost:3000 WebSocket URL of the Z-Wave JS Server.

Use with Claude Code

claude mcp add zwave-js-ui \
  --env ZWAVE_JS_URL=ws://borg:3002 \
  -- uvx mcp-server-zwave-js-ui

Or add it to an MCP client config directly:

{
  "mcpServers": {
    "zwave-js-ui": {
      "command": "uvx",
      "args": ["mcp-server-zwave-js-ui"],
      "env": { "ZWAVE_JS_URL": "ws://borg:3002" }
    }
  }
}

Tools

Tool Description
zwave_controller_info Controller and network summary (home id, versions, RF region, node counts).
zwave_list_nodes One-line summary of every node (status, readiness, security, device).
zwave_node_info Full detail for a node (device class, command classes, endpoints, signal).
zwave_node_values A node's current values, excluding configuration parameters.
zwave_node_config A node's configuration parameters with current values and metadata.

Roadmap

  • Level 2 — read/write: set values (on/off/dim), set configuration parameters, manage association groups. Mutating tools will be gated behind a ZWAVE_JS_READ_ONLY flag.
  • Level 3 — admin/lifecycle: inclusion/exclusion, re-interview, network heal / rebuild routes, OTA firmware update.

Development

git clone https://github.com/cacack/mcp-server-zwave-js-ui
cd mcp-server-zwave-js-ui
uv venv --python 3.13 && source .venv/bin/activate
uv pip install -e ".[dev]"
pytest
ruff check . && ruff format --check .

See CLAUDE.md for architecture and design notes.

License

MIT

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