{
  "markdown": "# Weather — Current Conditions and Forecast\n\nCurrent weather and 7–10 day forecast for any location. Backed by Open-Meteo (https://open-meteo.com), a free aggregator of national meteorological agency data (NOAA in the US, DWD in Germany, etc.). Returns temperature, humidity, wind, precipitation, conditions. Free, no auth, no API key.\n\nPart of [Pipeworx](https://pipeworx.io) — an MCP gateway connecting AI agents to 1476+ live data sources.\n\n## Why this matters for AI agents\n\nWeather is one of those things agents need to know about constantly — for travel planning, agricultural questions, energy demand context, event planning, real estate (\"is this market in a flood zone with active flooding?\"). Open-Meteo is the right backend: free, accurate, global coverage, no key gymnastics.\n\nCommon flows:\n\n- **Current conditions.** \"Weather in Tokyo right now\" → `get_weather({location: \"Tokyo\"})` → temp, humidity, wind, conditions.\n- **Forecast.** \"7-day forecast for Denver\" → `get_forecast({location: \"Denver\"})` → daily highs/lows, precipitation chance.\n- **By coordinates.** `get_weather({latitude: 39.74, longitude: -104.99})` for places that don't geocode well by name.\n\n## Auth\n\nNone. Open-Meteo is free and unauthenticated. Generous fair-use limits (~10,000 requests/day per IP). Pipeworx caches per-location for short windows so repeated calls don't burn your daily quota.\n\n## Geocoding\n\nThe `location` parameter accepts:\n- City names (`\"Tokyo\"`, `\"London\"`, `\"Denver\"`)\n- City + country (`\"Paris, France\"` to disambiguate from Paris, TX)\n- ZIP/postal codes (`\"94070\"` for US, `\"SW1A 1AA\"` for UK)\n- Coordinates as a separate `latitude` + `longitude` argument\n\nFor ambiguous names, the tool returns a disambiguation hint. For weird locations or precision-sensitive queries (offshore, remote), pass coordinates directly.\n\n## Update cadence\n\n| Data | Refresh |\n|---|---|\n| Current conditions | ~10 minutes |\n| Hourly forecast (next 24h) | Every 1–3 hours |\n| Daily forecast (1–10 days) | Every 6 hours |\n\nPipeworx caches with a 10-minute TTL so repeated calls within that window are cheap.\n\n## Common pitfalls\n\n- **Time zones.** Forecast hours are in UTC by default. The tool also returns the location's timezone — convert client-side when displaying to users.\n- **Precipitation probability vs. amount.** \"70% chance of rain\" and \"0.4 inches expected\" are different fields. For agricultural and travel use, both matter; report both.\n- **Forecast accuracy degrades by day.** Day 1 is reliable; day 7+ is \"directional weather signal.\" Don't quote 10-day forecasts as confident predictions.\n- **Severe weather events.** Open-Meteo has hazard fields but they're less reliable than NWS active alerts for the US. For severe weather agents, layer NOAA NWS API on top.\n- **Historical weather.** Default tools are present + future. For historical data (yesterday and back), Open-Meteo has separate endpoints — let the team know via [pipeworx_feedback](/docs/concepts/meta-tools) if that's needed.\n\n## Quick Start\n\nAdd to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):\n\n```json\n{\n  \"mcpServers\": {\n    \"weather\": {\n      \"url\": \"https://gateway.pipeworx.io/weather/mcp\"\n    }\n  }\n}\n```\n\n### What this endpoint actually serves\n\n`tools/list` at `https://gateway.pipeworx.io/weather/mcp` returns the tools in the table\nabove **plus the shared Pipeworx meta-tools** — `ask_pipeworx`,\n`discover_tools`, `search_within`, `remember`/`recall` and the rest of the\ngateway-wide set. So the tool count you see is larger than this table: a\nsingle-pack endpoint currently lists roughly 30 shared tools alongside the\npack's own. The connection's `initialize` response states its exact scope, and\nis the authoritative answer for a given day.\n\nThis is deliberate, not multiplexing by accident. The meta-tools are what let a\nscoped connection answer a question this pack does not cover — via\n`ask_pipeworx`, which routes across the whole catalog — without you adding a\nsecond MCP server. There is currently no way to mount a pack endpoint without\nthem; if the extra schemas cost you more context than the routing is worth,\nconnect to the full gateway once rather than to several pack endpoints.\n\nOr connect to the full Pipeworx gateway to get every pack's tools listed\ndirectly, instead of just this one's:\n\n```json\n{\n  \"mcpServers\": {\n    \"pipeworx\": {\n      \"url\": \"https://gateway.pipeworx.io/mcp\"\n    }\n  }\n}\n```\n\nBoth URLs reach the same gateway and the same 1476+ data sources. The\nonly difference is which pack's tools are listed **directly**; `ask_pipeworx`\nreaches all of them from either one.\n\n## Using with ask_pipeworx\n\nInstead of calling tools directly, you can ask questions in plain English —\nthis works on the pack endpoint above as well as on the full gateway:\n\n```\nask_pipeworx({ question: \"your question about Weather data\" })\n```\n\nThe gateway picks the right tool and fills the arguments automatically.\n\n## More\n\n- [Docs and guides](https://pipeworx.io/docs)\n- [pipeworx.io](https://pipeworx.io)\n\n## License\n\nMIT\n",
  "bytes": 5024,
  "sha": "5f23178e6e59bb8c1bb9a2d3ba15a797166763dcb7eafc2f49da15413d1f3541",
  "repo_slug": "pipeworx-io/mcp-weather",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_pipeworx_io_weather_148e7eea/readme"
}