iaqualink-mcp
Enables AI assistants to monitor and control Jandy iAqualink pool and spa equipment, including device status, power toggling, temperature settings, and lighting effects.
README
iaqualink-mcp
An MCP server that exposes a Jandy iAqualink pool/spa system to Claude
(or any MCP client). It wraps the iaqualink
Python library.
Tools provided:
list_systems— all systems on the accountlist_devices— all devices on a systemget_device— state of one deviceget_system_status— system + every device's state in one callturn_on/turn_off/toggle_deviceset_temperature— thermostat set pointsset_light_effect/set_light_rgbw/set_light_brightness— ICL/IntelliCenter lights
Set IAQUALINK_READ_ONLY=true to disable every write tool and only allow reads.
Install
From GitHub (once pushed)
uv tool install git+https://github.com/jgonzalez007/iaqualink-mcp
From a local clone (recommended for development, and avoids uvx
having to clone/build the project on every launch)
git clone https://github.com/jgonzalez007/iaqualink-mcp
cd iaqualink-mcp
uv tool install .
Either way this registers a command called iaqualink-mcp that uvx/uv tool
can run directly.
Configure Claude Desktop
Edit %APPDATA%\Claude\claude_desktop_config.json (Windows) or
~/Library/Application Support/Claude/claude_desktop_config.json (macOS)
and add:
{
"mcpServers": {
"iaqualink": {
"command": "uvx",
"args": ["iaqualink-mcp"],
"env": {
"IAQUALINK_USERNAME": "you@example.com",
"IAQUALINK_PASSWORD": "your-iaqualink-password"
}
}
}
}
Add "IAQUALINK_READ_ONLY": "true" to env if you only want Claude to read
status, never control equipment.
Then fully quit Claude Desktop from the system tray (not just close the window) and relaunch it.
Development
git clone https://github.com/jgonzalez007/iaqualink-mcp
cd iaqualink-mcp
uv sync --extra dev
# Run tests
uv run pytest
# Lint
uvx ruff check .
Copy .env.example to .env and fill in your credentials for local manual
testing; .env is gitignored.
Contributing
Issues and pull requests are welcome. Please run pytest and ruff check .
before opening a PR.
Notes
- This uses a reverse-engineered/unofficial API (via
iaqualink-py); Jandy/ Zodiac/Fluidra don't publish an official one. Use at your own risk. - Credentials are read from environment variables only — nothing is written to disk by this server.
- Your
claude_desktop_config.jsonwill contain your iAqualink password in plaintext. Don't commit that file or share it, and treat it like any other credential store on your machine.
License
MIT — see LICENSE.
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.