
Connects Claude to Pirate Weather, a Dark Sky compatible forecast API. Exposes two tools: forecast for full weather data at a specific location, and forecast_grid for raw GFS/ECMWF model data. Routes through Pipeworx's gateway, which means you can either use this standalone or get it as part of their 250+ data source bundle. Supports their ask_pipeworx wrapper if you'd rather ask questions in natural language instead of calling tools directly. You'll need a free Pirate Weather API key. Reach for this when you need weather data in your Claude workflows without dealing with commercial API restrictions.
Pirate Weather MCP — Dark Sky-compatible forecast API. Free key required (10k/mo).
Part of Pipeworx — an MCP gateway connecting AI agents to 1476+ live data sources.
PLATFORM_PIRATEWEATHER_KEY. BYO: ?_apiKey=….forecast(lat, lon, time?, exclude?, extend?, lang?, units?) — full forecast at pointforecast_grid(lat, lon, time?, units?) — GFS/ECMWF grid outputexclude: comma-sep currently,minutely,hourly,daily,alerts. extend=hourly returns 168h. units: us (default) | si | ca | uk | uk2.
https://api.pirateweather.net
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"pirate-weather": {
"url": "https://gateway.pipeworx.io/pirate-weather/mcp"
}
}
}
tools/list at https://gateway.pipeworx.io/pirate-weather/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 Pirate Weather data" })
The gateway picks the right tool and fills the arguments automatically.
MIT