
Connects Claude to the US National Weather Service API without needing authentication. Runs through Pipeworx's gateway infrastructure, which also offers access to 250+ other data sources if you need them. The server supports their ask_pipeworx natural language interface, so you can ask weather questions in plain English instead of calling specific tools. Useful when you're building assistants that need current US weather data, forecasts, or NWS alerts and don't want to manage API keys or deal with rate limiting yourself. Available via streamable HTTP, so setup is just dropping a URL into your MCP client config.
US National Weather Service MCP — authoritative US forecasts + alerts. No auth.
Part of Pipeworx — an MCP gateway connecting AI agents to 1476+ live data sources.
get_forecast(latitude, longitude) — 7-day text forecast for a US lat/lon.get_hourly_forecast(latitude, longitude, max_hours?) — hourly forecast.get_alerts(area?, latitude?, longitude?, severity?, urgency?, event?, limit?) — active watches/warnings/advisories.get_observation(station_id) — latest observation from an ICAO station.https://api.weather.gov — public, no key. NWS requests a unique User-Agent header on every request; this pack sends Pipeworx-NWS-MCP/0.1 (contact@mojibake.ai).
US locations only.
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"nws": {
"url": "https://gateway.pipeworx.io/nws/mcp"
}
}
}
tools/list at https://gateway.pipeworx.io/nws/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 1476+ data sources. The
only difference is which pack's tools are listed directly; ask_pipeworx
reaches all of them from either one.
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 Nws data" })
The gateway picks the right tool and fills the arguments automatically.
MIT