Skip to main content

MCP server for air-Q Cloud API — access air quality data from anywhere

Project description

mcp-airq-cloud

MCP PyPI Total Downloads Python License Tests Coverage

MCP server for the air-Q Cloud API — access air quality data from anywhere.

Unlike mcp-airq (which communicates directly with devices on the local network), this server uses the air-Q Cloud REST API to retrieve sensor data remotely.

The same mcp-airq-cloud executable also works as a direct CLI when you pass a tool name as a subcommand.

Tools

Tool Description
list_devices List configured air-Q Cloud devices
get_air_quality Get latest sensor readings (supports device/location/group selection)
get_air_quality_history Get historical data within a time range as column-oriented JSON
plot_air_quality_history Render one historical chart per sensor across all matching devices
export_air_quality_history Export one historical sensor as one csv or xlsx across matching devices

All tools are read-only — the Cloud API does not support device configuration or control.

Installation

pip install mcp-airq-cloud

Or install from source:

git clone https://github.com/CorantGmbH/mcp-airq-cloud.git
cd mcp-airq-cloud
uv sync --frozen --extra dev

CLI Usage

Use the same command directly from the shell:

mcp-airq-cloud list-devices
mcp-airq-cloud get-air-quality --device "Living Room"
mcp-airq-cloud get-air-quality-history --device "Living Room" --last-hours 24 --sensors co2 pm2_5
mcp-airq-cloud plot-air-quality-history --sensor co2 --output-format png --output co2.png
mcp-airq-cloud export-air-quality-history --sensor co2 --output-format xlsx --output co2.xlsx

For historical plots and exports:

  • omit device, location, and group to combine all configured devices into one artifact
  • use location or group to combine only the matching devices
  • plot_air_quality_history returns one file per requested sensor, with one series per matching device
  • export_air_quality_history returns one CSV/XLSX file per request, with rows for all matching devices

The CLI subcommands mirror the MCP tool names. Both styles work:

mcp-airq-cloud list-devices
mcp-airq-cloud list_devices

To force MCP server mode from an interactive terminal, run:

mcp-airq-cloud serve

The CLI is pipe-friendly: successful command output goes to stdout, while tool errors go to stderr with exit code 1. Plot commands can also stream directly to stdout.

mcp-airq-cloud get-air-quality --device "Living Room" | jq '.co2'
mcp-airq-cloud get-air-quality-history --device "Living Room" --compact-json | jq '.columns.co2'
mcp-airq-cloud get-air-quality-history --device "Living Room" --yaml | yq '.columns.co2'
mcp-airq-cloud plot-air-quality-history --sensor co2 --device "Living Room" --output - > co2.png
mcp-airq-cloud export-air-quality-history --sensor co2 --device "Living Room" --output - > co2.xlsx

Configuration

You need a Cloud API key and the 32-character device ID for each device. Both can be obtained at my.air-q.com.

Option 1: Environment variable (inline JSON)

export AIRQ_CLOUD_DEVICES='[{"id": "de45d2ed777780c96c0deae7a220b745", "api_key": "your-api-key", "name": "Living Room"}]'

Option 2: Default config file (recommended)

Place a JSON file at ~/.config/airq-cloud-devices.json — no environment variable needed:

[
  {"id": "de45d2ed777780c96c0deae7a220b745", "api_key": "your-api-key", "name": "Living Room"}
]

Option 3: Custom config file path

export AIRQ_CLOUD_CONFIG_FILE=/path/to/devices.json

Option 4: Global API key

If all devices share the same API key, set it once:

export AIRQ_CLOUD_API_KEY="your-api-key"
export AIRQ_CLOUD_DEVICES='[{"id": "de45d2ed777780c96c0deae7a220b745", "name": "Living Room"}]'

Device config fields

Field Required Description
id yes 32-character cloud device ID
api_key no Per-device API key (falls back to AIRQ_CLOUD_API_KEY)
name no Friendly name (defaults to first 8 chars of ID)
location no Location for grouping (e.g. "Wohnzimmer")
group no Group for grouping (e.g. "zu Hause")

Usage with Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "air-Q Cloud": {
      "command": "mcp-airq-cloud",
      "env": {
        "AIRQ_CLOUD_DEVICES": "[{\"id\": \"<device-id>\", \"api_key\": \"<key>\", \"name\": \"Living Room\"}]"
      }
    }
  }
}

Usage with Claude Code

claude mcp add air-Q-Cloud mcp-airq-cloud \
  -e AIRQ_CLOUD_DEVICES='[{"id":"<ID>","api_key":"<KEY>","name":"<Name>"}]'

Development

uv sync --frozen --extra dev
uv run pre-commit install
uv run pytest

The repository uses a project-local .venv plus uv.lock for reproducible tooling. Run developer commands through uv run, for example:

uv run ruff check .
uv run ruff format --check .
uv run pyright
uv run pre-commit run --all-files

License

Apache 2.0 — see LICENSE.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

mcp_airq_cloud-1.4.4.tar.gz (197.8 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

mcp_airq_cloud-1.4.4-py3-none-any.whl (29.7 kB view details)

Uploaded Python 3

File details

Details for the file mcp_airq_cloud-1.4.4.tar.gz.

File metadata

  • Download URL: mcp_airq_cloud-1.4.4.tar.gz
  • Upload date:
  • Size: 197.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for mcp_airq_cloud-1.4.4.tar.gz
Algorithm Hash digest
SHA256 9d3ee73267eff30bdb977bd2b264a3785b4590e7ca7f931dbac2d03d10753b57
MD5 2cfa328b67d3026fdfbd62f019fa4412
BLAKE2b-256 8ee9b85fb592b45a5aa7eaaff36e35ead51134e844ae8d5c5c417d1617f7daf6

See more details on using hashes here.

Provenance

The following attestation bundles were made for mcp_airq_cloud-1.4.4.tar.gz:

Publisher: publish.yml on CorantGmbH/mcp-airq-cloud

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file mcp_airq_cloud-1.4.4-py3-none-any.whl.

File metadata

  • Download URL: mcp_airq_cloud-1.4.4-py3-none-any.whl
  • Upload date:
  • Size: 29.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for mcp_airq_cloud-1.4.4-py3-none-any.whl
Algorithm Hash digest
SHA256 0eb758f690f1a0a820da4ba7c91a3a5ea3ee5e9412eab05bbee909ec3b445c48
MD5 0a81d31a7c8659a83049f331396d4b6a
BLAKE2b-256 f76b750cb250755711a5bd3280beb49da802ad3e7f784669c6c99567116faf9b

See more details on using hashes here.

Provenance

The following attestation bundles were made for mcp_airq_cloud-1.4.4-py3-none-any.whl:

Publisher: publish.yml on CorantGmbH/mcp-airq-cloud

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page