Weather That Doesn't Suck MCP Server

Finds the best time on a day for an activity. Returns the best window, an alternate, and any clearly bad stretch, each with a short reason. Windows are stretches, not exact hours: when several start times are about equally good they are reported as one stretch, and when the whole day is about the same it says so. Use it for "when should I go?", "what's the best time Saturday?", "Kilian and I want to hike Saturday". Give a date such as "Saturday", "tomorrow" or 2026-10-03. If nothing on the day is good it says so and names the least bad stretch.

What to wear for an activity at a time and place, short and practical, followed by the weather it rests on. It dresses you for the effort, not just the temperature: a runner is warmer than a person standing still at the same feels-like, and the same rules as the website's outfit card apply. Optional: intensity, and preferences such as { "feel": "runs_cold" } or { "avoid": ["shorts"] }.

Explains weather in plain terms for conversation: why it feels colder than the temperature, whether rain will matter on a hike, whether wind matters, whether the trail will be muddy, humidity, fog, frost, pressure. It separates what the forecast says (facts, each labelled forecast or formula) from what we are reasoning (inferences, each with its basis and how sure we are) and lists what we cannot see (unknowns). Pass the question as asked, or a topic. If it cannot tell what was asked it says so and gives the general picture.

Compatibility tool for ChatGPT connectors. Returns the weather for an id from `search`. For real use prefer get_weather.

The forecast for a stretch of time: "What's Saturday looking like?", "What will conditions be between 6 PM and midnight?", "this weekend". Give start_time (and optionally end_time or duration_hours). Returns a one-line summary, the temperature range, rain, wind, any conditions worth acting on, and the hourly and daily rows. The forecast reaches about seven days. Beyond that it says so and does not guess.

Our flagship tool. Turns weather into a decision for a specific outdoor activity: a practical verdict (go, go_with_caveats, marginal, no_go), a one-sentence reason, the temperature and feels-like range, rain, wind, sunset, what to wear, and the concerns. Activities: walking, hiking, trail_running, road_running, cycling, camping, hunting, fishing, yard_work, construction, painting_finishing, general_outdoor. Give a start_time and a duration_hours, or a phrase like "tomorrow morning". If you name a whole day ("Saturday"), it finds and judges the best window inside it. It keeps the forecast apart from our advice, says what it is inferring (mud, ice, fog) and what it cannot know (the trail surface), and an official warning overrides everything. To find WHEN to go, use find_best_weather_window.

What weather you will meet as you move along a route, at the moment you reach each part of it. Not "the weather on the trail" but "what will I encounter, where, and when". Accepts a known trail_id, a GPX file, GeoJSON, an encoded polyline, coordinates, or place names. With a start_time and a pace it works out when you reach each checkpoint, reads the forecast for that place at that time, and reports what changes: rain starting, the cold coming in, the light going. For someone already out there, pass `progress` (how far they are, or where) and it answers for the rest of the route from now. Returns checkpoints with arrival time, place, weather and light, the changes, and a bottom line. Use get_trail_weather for an hour-by-hour timeline and clothing advice.

Compatibility tool for ChatGPT connectors. Finds places matching a query and returns ids to pass to `fetch`. For real use prefer get_weather, outdoor_activity_weather and the other tools, which answer directly.

Weather for a trail over time, sampled along the trail rather than at one point: starting conditions, how the temperature changes through the trip, rain windows, wind and gusts, humidity and dew point, wind chill and heat index, sunrise, sunset, twilight, the moon, significant changes, alerts, and what to wear and carry. Give a trail_id (call list_trails) or the route itself, plus start_time and a pace or total_duration_hours. Returns a timeline every two hours and a bottom line. It does not know the terrain, shade or exposure unless the trail record says so, and it says that.

Lists the trails WTDS knows by name, with length, bounds and whether we have data on which sections are exposed. Use a trail's id as trail_id in get_trail_weather or route_weather. If a trail is not listed, send the route itself.

Plain-language weather for a place: one sentence first, then current conditions, the next 24 hours, the next 7 days, and official alerts. Use it for "what's the weather", "do I need a jacket", "is it going to rain". For a decision about doing something outdoors (a run, a hike, staining a deck), use outdoor_activity_weather instead: it answers "should I?", not just "what is it?". `data.current` says whether it is a station observation, a model estimate, or a forecast hour. `data.alerts.status` says whether "no alerts" can be believed: only "ok" means we checked. Answers carry their sources, how old the data is, and say so when it came from cache.