Skip to main content

air-quality-mcp

Real, current air quality (US AQI, PM2.5, PM10, ozone, and more) for any city, free, in one command.

pip install air-quality-mcp   # or: uvx air-quality-mcp

Then ask your agent: "what's the air quality in Bangkok?" or "is it safe to run outside in Berlin today?"

No API key. No signup. Free.

Tools

Tool What the model sees it for
get_air_quality(city) Current air quality for a city -- US AQI, PM2.5, PM10, ozone, NO2, SO2, CO, plus a plain-language category. "What's the air quality in X", "is it safe to go outside in Y", "how polluted is Z".

city is a free-text place name (e.g. "Bangkok", "Berlin", "Springfield, US").

Example

> get_air_quality("Bangkok")
{
  "location": {
    "name": "Bangkok",
    "country": "Thailand",
    "admin1": "Bangkok"
  },
  "us_aqi": 27,
  "aqi_category": "Good",
  "pm2_5": 5.4,
  "pm10": 6.4,
  "ozone": 36.0,
  "nitrogen_dioxide": 14.1,
  "sulphur_dioxide": 3.9,
  "carbon_monoxide": 1861.0,
  "local_time": "2026-08-06T20:00",
  "attribution": "Air quality data by Open-Meteo (open-meteo.com)"
}
> get_air_quality("Berlin")
{
  "location": {
    "name": "Berlin",
    "country": "Germany",
    "admin1": "State of Berlin"
  },
  "us_aqi": 51,
  "aqi_category": "Moderate",
  "pm2_5": 5.5,
  "pm10": 9.6,
  "ozone": 102.0,
  "nitrogen_dioxide": 2.6,
  "sulphur_dioxide": 1.0,
  "carbon_monoxide": 145.0,
  "local_time": "2026-08-06T15:00",
  "attribution": "Air quality data by Open-Meteo (open-meteo.com)"
}

aqi_category is computed from us_aqi using the standard US AQI bands: 0-50 Good, 51-100 Moderate, 101-150 Unhealthy for Sensitive Groups, 151-200 Unhealthy, 201-300 Very Unhealthy, 301+ Hazardous. It comes back as "Unknown" on the rare grid cell where no AQI can be resolved.

How it's free

This server is part of the Lulu Ads network: tool results may carry one clearly labeled, disclosed sponsored data field (never instructions, never hidden). That sponsorship pays the hosting, so the lookup stays free. Fail-open by design — if the ads backend is slow, down, or (as with a local install) has no credentials at all, the tools behave exactly like an unmonetized server.

Run your own MCP? The same one-line integration is open to every publisher — getlulu.dev/publishers, 70% rev share.

Data

Air quality data by Open-Meteo (free, no API key required). This project is not affiliated with Open-Meteo.

Self-hosting over HTTP

pip install fastmcp lulu-ads httpx uvicorn
MCP_TRANSPORT=http AIRQUALITY_LOCAL_DEV=1 python server.py   # serves http://localhost:8080/air-quality/mcp

Metadata

Release files for air-quality-mcp 0.1.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Built distribution (wheel)

Table of built distributions (wheels) for air-quality-mcp 0.1.0
File Interpreter ABI Platform
air_quality_mcp-0.1.0-py3-none-any.whl Python 3 none any Details

Release files / air_quality_mcp-0.1.0-py3-none-any.whl

Download URL air_quality_mcp-0.1.0-py3-none-any.whl
Size 7.0 kB
Tags Python 3
SHA-256 checksum
How to use checksums
806eeda6f211b17edb7f80ae9c91d6820d66020109b8e4bb3c44c40e57e5693c
BLAKE2b-256 checksum
How to use checksums
30726919e15d37c53923da27903e28c790eed429d8619fe5adf2323135dd817f
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.14.2

Release history Release notifications | RSS feed

This release

0.1.0 This release

1 release file

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page