EPA AirNow MCP — official US real-time AQI + forecast (free key)
SaferSkills independently audited Mcp Airnow (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
US EPA AirNow — official current and forecast air quality index (AQI) for every US reporting area, plus hourly per-site monitor observations. Keyless: reads AirNow's public file products on files.airnowtech.org live per call.
Part of Pipeworx — an MCP gateway connecting AI agents to 1856+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.
AirNow *retired its keyed web service (`www.airnowapi.org/aq/) on 2026-10-01**; every call returned HTTP 410 until this pack was moved to the file products (fleet #2808). The retired-service notice at docs.airnowapi.org/webservices/retired` redirects to a login page, so the file products are the only public route left.
current_by_zip(zip_code, distance_miles?) — latest observed AQI perpollutant for the reporting area nearest a ZIP, with yesterday's AQI and the other reporting areas inside the radius.
current_by_location(latitude, longitude, distance_miles?) — same, for alat/lon.
forecast_by_zip(zip_code, date?, distance_miles?) — issued forecasts (today+ up to 3 days) per pollutant, with Action Day flag and forecaster discussion. Omit date for every issued day; forecast_days_available lists them.
observations_in_bbox(bbox, start_date, end_date, parameters?, data_type?, verbose?)— hourly per-site AQI and concentrations inside minLon,minLat,maxLon,maxLat for a span of UTC hours (YYYY-MM-DDTHH), max 24 hours per call (one ~1 MB upstream file per hour). Pollutants: OZONE, PM25, PM10, NO2, CO, SO2 (AQI exists for the first four only).
Every response carries data_as_of (the upstream file's Last-Modified), source (the file URL) and found. A miss is {found:false, reason, hint}: zip_not_in_airnow_index, no_reporting_area_in_radius, no_forecast_area_in_radius, no_forecast_for_date, hours_not_published, no_sites_in_bbox.
None. No key, no account.
All under https://files.airnowtech.org/airnow/ (an S3 bucket AirNow rewrites hourly; format fact sheets in airnow/docs/):
| File | Used by | Refresh |
|---|---|---|
today/cityzipcodes.csv — ZIP → city, state, lat, lon (27k rows) | *_by_zip | daily |
today/reportingarea.dat — per reporting area: yesterday (Y), current observed (O), forecast (F) rows | current_*, forecast_by_zip | hourly |
YYYY/YYYYMMDD/HourlyAQObs_YYYYMMDDHH.dat — per-site AQI + concentrations, one file per UTC hour | observations_in_bbox | ~30-60 min after the hour |
Quirks worth knowing:
category but a null AQI —that is how the agencies issue them, not a parse gap.
HourlyAQObs file does not exist until AirNow publishes it;those hours are listed in hours_not_yet_published rather than erroring.
centroid, so a ZIP on a metro edge may resolve to the neighbouring region (ZIP 10001 → "New York City Region", 10 mi). other_areas_in_radius shows the alternatives.
airnow results for 10 minutes(CACHE_TTL_OVERRIDES); the pack also keeps the parsed files in the isolate for 10 min (reporting area) / 24 h (ZIP index) / 6 h (hourly files).
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"airnow": {
"url": "https://gateway.pipeworx.io/airnow/mcp"
}
}
}tools/list at https://gateway.pipeworx.io/airnow/mcp returns the tools in the table above plus the shared Pipeworx meta-tools — ask_pipeworx, discover_tools, search_within, remember/recall and the rest of the gateway-wide set. So the tool count you see is larger than this table: a single-pack endpoint currently lists roughly 30 shared tools alongside the pack's own. The connection's initialize response states its exact scope, and is the authoritative answer for a given day.
This is deliberate, not multiplexing by accident. The meta-tools are what let a scoped connection answer a question this pack does not cover — via ask_pipeworx, which routes across the whole catalog — without you adding a second MCP server. There is currently no way to mount a pack endpoint without them; if the extra schemas cost you more context than the routing is worth, connect to the full gateway once rather than to several pack endpoints.
Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}Both URLs reach the same gateway and the same 1856+ data sources. The only difference is which pack's tools are listed directly; ask_pipeworx reaches all of them from either one.
curl -X POST https://gateway.pipeworx.io/v1/tools/current_by_zip \
-H 'Content-Type: application/json' \
-d '{"zip_code":"10001"}'No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/current_by_zip. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.
@pipeworx/mcp-airnow is a local stdio bridge to the Pipeworx gateway: your MCP client starts it with npx, and it forwards every call to the same https://gateway.pipeworx.io/airnow/mcp endpoint shown above. It needs network access; there is no offline mode.
{
"mcpServers": {
"airnow": {
"command": "npx",
"args": ["-y", "@pipeworx/mcp-airnow"]
}
}
}Without a key it calls anonymously, capped at 50 calls a day. A free account raises that to 200 a day: get a key at https://pipeworx.io/signup and add "env": { "PIPEWORX_API_KEY": "<your key>" } to the server entry. The key is sent as a Bearer token, the same way a hosted connection sends it, so calls are metered and billed exactly as they are there.
It lists only this pack's tools by default. Set PIPEWORX_META_TOOLS=1 to also list ask_pipeworx and the other gateway-wide tools.
Behind an HTTPS proxy: Node's built-in fetch does not read HTTPS_PROXY by default. Newer Node releases honour it when NODE_USE_ENV_PROXY=1 is set; check your Node version's documentation.
Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:
ask_pipeworx({ question: "your question about Airnow data" })The gateway picks the right tool and fills the arguments automatically.
MIT
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.