Smarter Weather MCP server

• call_toolwrite actionFree

  Runs a tool find_tools lists, by name: same price, limits and result as calling it directly. Tools already in your list are called directly, not through this. `arguments` follows that tool's input schema.

• describe_dataFree

  A dataset's variables or properties (standard names, units, categories, bands, aggregates), horizon, step, cadence, freshness, cost class, verified `examples` and an example_query to read its values. Free; call it after search_data, before get_data. Example: {"dataset_id": "<from search_data>"}.

• find_placesFree

  Find places: a name, ZIP, venue or address to ranked candidates with lat/lon, or coordinates to the place and timezone. Pass `query` (fuzzy=true for partial input) or `lat`+`lon`; rows carry `type` place|zip|address|poi, `matched_via: "autosuggest"` marks fallback rows and `partial` a timed-out section. Weather tools take `location`; use this to disambiguate or name a point. Example: {"lat": 39.74, "lon": -104.99} -> Denver, Colorado, America/Denver.

• find_toolsFree

  Lists the weather tools this connection does not show (best times, routes, air quality; station observations, soundings, hurricane recon; lightning, storm cells, storm reports; outlooks, forecaster text, hurricanes; climate records and normals; forecast accuracy; maps and charts; crop heat units), with when to use each and its required arguments. Run one with call_tool, in this session, no reconnect. With `tools`, returns their full input schemas. Free; no network call.

• get_alertsFree

  NWS watches, warnings, advisories. Point (city/ZIP/lat+lon): containing polygons. BBox or US state/DC/CONUS (codes, full names, US/national): intersecting polygons. A city miss is not a statewide all-clear — query the state or a bbox; never say regional inventory is impossible. NY/WA and "New York State"/"Washington State" are states; "New York"/"Washington" stay cities. Omit at for now; at (ISO-8601 UTC) is the snapshot then. Empty = all-clear or purged (~24h). alert_id = detail+geometry, ignores at. Ex: {"location":"WI","events":["Tornado Warning"]}.

• get_current_conditionsFree

  Current weather right now at a location from two independent sources in one call: the RTMA gridded analysis (exact-point values, updated sub-hourly) and the nearest METAR station observation (ground truth with raw METAR, flight category). Use the analysis for point-accurate values and the station for verification. Analysis fields: temperature_2m, dew_point_2m, relative_humidity_2m (derived here from temperature and dew point; listed in analysis.derived), wind_speed_10m, wind_direction_10m, wind_gusts_10m, surface_pressure (station pressure at ground level, not sea-level pressure), visibility, cloud_cover, cloud_ceiling, in units (labels in analysis.unit_labels). nearest_station is the station's own report, unconverted. For a forecast, use get_forecast. Example: {"location": "Pella, IA"}.

• get_dataFree

  Values, totals, comparisons, people and POI counts from any catalog dataset (models, radar, alerts, outlooks, reference layers) at a place or several, over a bbox or area, or as items. `select` takes `product:variable` or `product:property` tokens, a standard name or a concept such as `population`; send one space word (an `area` reference is `{product, feature_id}`) and at most one time word (hours, start+end or at; run pins a cycle); `stats` reduces per `step` or over the area; omit units for SI. Example: {"select": ["nbm_conus:temperature_2m"], "location": "Denver, CO", "hours": 24}.

• get_forecastFree

  Forecast for a US place: current conditions, daily forecast with sunrise and sunset, active alerts and outlooks in one call, and hour by hour with include=hourly. Blended across NBM, HRRR, GFS, RTMA and SPC and unit-converted server-side; times are UTC ISO 8601, quote daily[].astro.local as local, and if forecast.location.timezone_resolved is false state times as UTC. For hours set `hours` (next N, default 48) or `start`+`end` for one stretch hour by hour, and check hourly_coverage (first_time, last_time, sample_interval_hours, truncated) before answering about a specific hour; past last_time say the forecast does not reach that far. Example: {"location": "Portland, OR", "include": "hourly", "hours": 24}.

• get_forecast_distributionFree

  NBM probabilistic guidance for one weather aspect: percentiles (p10-p90), exceedance probabilities and ensemble spread. Use this for any question about odds, ranges, potential or confidence ("how much could we get", "range of possible highs", "how sure is this") -- a deterministic forecast value cannot answer one. Reading the percentiles: p50 is the most likely outcome, p90 is the reasonable worst case when the risk is the high end (snow totals, wind, rainfall), and p10 when the risk is the low end (cold, visibility, ceiling). A single percentile is not the forecast -- report the likely value with the tail that matters, and label which is which. Aspects: precip (PoP, QPF + percentiles), snow (accumulation percentiles, >1/2/4in probabilities, snow level, snow-type probability), ice (ice accretion, freezing-rain / ice-pellet probabilities), temperature (`daily` high/low p10/p50/p90: the NBM value -/+ 1.28 stddev; hourly temp + stddev), wind (speed/gust percentiles), severe (thunderstorm probability plus NBM CWASP, a severe-environment index, both in percent: severe_weather_prob_p50 is the median CWASP value and severe_weather_prob_above_75 the probability CWASP exceeds 75; NBM has no tornado, hail or damaging-wind odds; SPC's: get_outlooks (guidance) hazard=severe), aviation (LIFR/IFR/MVFR visibility + ceiling odds), confidence (ensemble stddev; low = settled, high = details still in play). Labels in unit_labels. Example: {"location": "Denver, CO", "aspect": "snow", "hours": 72}.

• get_observed_precipitationFree

  How much rain fell: observed precipitation totals at a location. Use for "did it rain", "how much rain fell", "rain in the last 24 hours / since yesterday". Source: MRMS MultiSensor QPE Pass2 (radar bias-corrected to rain gauges) over 1/3/6/24/48/72 h windows (CONUS; 1 h only in Alaska and Hawaii). Values have about 2 mm (0.08 in) resolution, so 0 means under about 1 mm; data runs about an hour behind real time. Pass `at` (within 33 h) for totals ending at a past time (newest frame up to 3 h before it). With include_nowcast (default) it also returns a next-hour radar nowcast (CONUS): peak intensity (light/moderate/heavy), type and start time, not an amount. Forecast totals past the next hour: get_data (catalog); station reports: get_observations (observed).

• get_statusFree

  Data freshness of the weather platform (no inputs needed; refreshed about every 5 minutes): overall state, per-source states (ok / degraded / outage / no_signal), open incidents with their cause (provider outage vs internal processing delay) and active provider advisories. Use it when asked whether data is current, when other tools return stale-looking data, or before presenting time-critical weather. If a source is degraded or in outage, say the data may be stale rather than presenting it as live. Example: {}.

• get_time_contextFree

  Complete temporal context for a location: local time, timezone, 14-day calendar with day names and Today/Tomorrow offsets, sunrise/sunset/solar times (from the weather pipeline's astro product), and moon phase. Use whenever you need to reason about dates, times, or daylight for a location -- including "what time is sunset?", "is it dark there now?", or "what day of the week is the 4th-day forecast?". If current_time.timezone_resolved is false, zone unknown: state times as UTC, never as local. Accepts a place name directly. Example: {"location": "Seattle, WA"}.

• search_dataFree

  Search the data catalog: which dataset's values answer a weather question, or what data exists at a point. With `query` it ranks grids, radar, satellite, outlooks and observations and returns hits with variable, units, cadence, why, the exact `call` to run next and any verified `example`; without it, it lists datasets at the place with freshness, or every public one. A place (`location` or lat/lon) or `domain` keeps datasets covering it; variables come from describe_data. Example: {"location": "Anchorage, AK"}.

• Code scan7 source files scanned25/25
• Live reliabilityremote reachable in 784ms20/20
• Tool poisoning13 tool descriptions checked15/15
• Auth qualityopen endpoint exposes 1 write-action tools with no auth3/15
• Maintenancelast push 1 days ago15/15
• Maintainer identityregistry namespace matches repository owner7/10

Safety score

85/100

higher than 78% of 679 Maps and travel servers

Tools

13

the typical Maps and travel server has 6

Tools that change things

8%

typical: 0%. Fewer write tools means less an agent can break

Uptime

100%

of our recent checks; the typical remote Maps and travel server answers 100%

Response time

134 ms

faster than 80% of 450 Maps and travel servers

GitHub stars

1

more than 65% of 323 Maps and travel servers

Downloads a week

82

more than 63% of 152 Maps and travel servers with a package

Smarter Weather: common questions

Is Smarter Weather MCP server safe?

Yes, by our scan: it is graded A (85/100). Read the Smarter Weather safety report

How do I install Smarter Weather?

It runs remotely at mcp.smarterweather.com. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.

Does Smarter Weather need an API key?

Yes. The registry entry asks for SMARTERWEATHER_API_KEY.

Is Smarter Weather maintained?

The last commit was 6 days ago (2026-10-30). The latest release is v0.1.1.

Is Smarter Weather up?

100% of our last 28 checks got an answer. We check remote servers about four times a day.

What can I use instead of Smarter Weather?

Servers from other publishers that do the same job: Weather Data MCP Server, Nws Weather MCP server and Weather MCP server. Compare all Smarter Weather alternatives.

How does Smarter Weather compare with other Maps and travel MCP servers?

safety score 85/100 (higher than 78% of 679 Maps and travel servers); tools 13 (the typical Maps and travel server has 6); tools that change things 8% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.