Weather That Doesn MCP server

Which MCP servers are Weather That Doesn's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-25

← Back to Weather That Doesn

Whose server it is

Registry namecom.weatherthatdoesntsuck/weatherverified in the MCP registry

The registry name sits under weatherthatdoesntsuck.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-25

Stateanswerschecked 2026-10-25
Tools11
Server calls itselfweather-that-doesnt-suck
Server version1.0.0
Protocol version2025-06-18

On 2026-10-25 the server answered initialize and tools/list without a sign-in. First answer in 86 ms.

Should an agent connect itNot proven either way yet

Whether its tools do the product's job has not been judged yet.
Checked on 2 of the 7 days it takes to judge reliability.

Once connected

For "check whether to run or ride today", the likely first call is outdoor_activity_weather.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 2, the first on 2026-10-26

INITE MCP scoreafter a weeka score needs 7 daily checks: 2 so far
Answeredmeasuring2 of the 7 daily checks it takes to print a share
Median first answer271 ms
Space in an agent's context≈ 6,206 tokensthe definitions of all its tools (11), which an agent carries on every turn
Tool definitionsA · 97 of 100
Typed results0 of 11 toolsdeclared outputSchema: results come typed, read once

Parameters without a type: in 2 of 11

What an agent can do with it

can do · check whether to run or ride today
not sure · plan the commute around rain and ice
not sure · decide when to mow or skip the sprinklers

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers11 tools · read 2026-10-25

get_weather
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…
get_forecast
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…
outdoor_activity_weather
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…
find_best_weather_window
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…
clothing_recommendation
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…
explain_weather
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…
get_trail_weather
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…
route_weather
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…
list_trails
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.
search
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.
fetch
Compatibility tool for ChatGPT connectors. Returns the weather for an id from `search`. For real use prefer get_weather.

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "weather": {
      "type": "http",
      "url": "https://weatherthatdoesntsuck.com/api/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http weatherthatdoesntsuck https://weatherthatdoesntsuck.com/api/mcp

Add to Cursor Add to VS Code

claude.ai, ChatGPT and other clients: add https://weatherthatdoesntsuck.com/api/mcp as a custom connector in the settings.

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.