KaiCast Ocean Conditions
Server Details
Ocean conditions by location: water visibility, swell, wind, tide, plus dive and snorkel spot picks.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 6 tools
Each tool occupies a distinct decision axis: rank days (best_day), rank months (best_months), rank spots (recommend_spot), fetch facts for one spot (get_conditions), fetch climatology for a place (get_seasonality), or enumerate coverage (list_coverage). The closest pair is best_months vs get_seasonality, since both answer 'what is month X like', but one ranks and the other reports facts, and the descriptions make the distinction explicit. Minor residual risk that an agent picks best_day when it wanted a spot ranking, but the 'versus runner-up' / 'ranked top picks' framing differentiates them.
Five of six names are a clean verb_noun pattern (get_conditions, get_seasonality, list_coverage, recommend_spot, and arguably best_day/best_months as 'best_' + noun). The 'best_*' prefix is used as a consistent superlative family rather than a verb, which is a small but coherent deviation. No casing or stylistic chaos.
Six tools for a decision-support domain is well inside the sweet spot, and each maps to a non-redundant question type: facts, seasonality, day choice, month choice, spot choice, coverage. Nothing appears bolted on, and there is no pressure to merge distinct operations.
The surface covers the full planning lifecycle — coverage discovery, climatology, near-term facts, and ranked decisions across days, months, and spots — and gracefully reports uncovered/not-modeled states. Gaps are minor: there is no plain 'list spots in area' or 'get spot detail/metadata' call independent of ranking or conditions, so browsing a region without an activity in mind requires an indirect route.
Available Tools
6 toolsbest_dayFind the best dayARead-onlyIdempotentInspect
Which day in a window (max 7 days) is best for an activity at a destination — a spot, a region, or lat+lon with a radius — and why, versus the runner-up. Returns every day's best score, confidence, caveats and a KaiCast spot card for the winner. Free during early access.
Inputs: activity (required), to, lat, lon, +4 more. Returns: best, days, schema, source, +4 more
best_monthsBest months for an activity or speciesARead-onlyIdempotentInspect
Ranks the calendar months for one thing at one place: an activity (dive, snorkel, freedive, whale_swim), a species (e.g. manta, whale shark), or calm seas / warm water / clear water. Says whether the ranking comes from multi-year data or curated research seasons, with confidence and caveats. A decision call: metered, free during early access.
Inputs: for (required), lat, lon, area, +2 more. Returns: for, area, basis, months, +3 more
get_conditionsGet ocean conditionsARead-onlyIdempotentInspect
Facts for ONE covered spot over up to 7 days: 3-hour forecast periods with condition score (0-100) and rating, water visibility (ft), swell height/period/direction, wind, tide state and height, water temperature, plus tide events and data quality. Pass a spot id, or lat+lon to use the nearest covered spot within 30 km. Free.
Inputs: to, lat, lon, from, +1 more. Returns: spot, schema, source, periods
get_seasonalityGet seasonality (trip planning)ARead-onlyIdempotentInspect
What a place is usually like in a given month, for trip planning months ahead: per month, sea-surface temperature (p10/p50/p90 °C), wave height (p50/p90 m), wind (p50/p90 m/s), share of rough days, model water visibility (p25/p50/p75 m, low confidence), tropical-cyclone frequency, wildlife seasons, access rules and best activities. Every field carries its sources; curated seasons are drafts pending local review. Pass an area id, a spot id, or lat+lon, and optionally a month range. Free.
Inputs: lat, lon, area, spot, +2 more. Returns: area, months, notice, schema, +1 more
list_coverageList KaiCast coverageARead-onlyIdempotentInspect
Which regions and spots KaiCast covers, and whether each region supports ranked decisions (spot picks and best-day answers) or facts only. Also lists supported activities and how directly each is modeled. Anywhere not listed is not covered. Free.
Inputs: region. Returns: schema, source, regions
recommend_spotRecommend spotsARead-onlyIdempotentInspect
Ranked top picks (max 5) for an activity in one area on one day — by region id, or lat+lon with a radius. Each pick has the best daylight window, why (from the published conditions), a confidence score with its factors, caveats, and a KaiCast spot card. Returns status "not_covered" / "conditions_only" / "activity_not_modeled" honestly instead of guessing. Activities: snorkel (native model), dive, freedive, spearfish (proxy model; spots in water closed to spearfishing are excluded), surf (not modeled). Free during early access.
Inputs: activity (required), lat, lon, date, +4 more. Returns: picks, schema, source, status, +3 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Live scuba dive planning: forecast windows, best-time climatology, species seasons, 4,800+ sites.
Real-time surf, weather, trail status, volcano, ocean safety, and restaurants for Hawaii.
Nearest NOAA buoy readings, tides and 7-day swell forecast for 150+ surf spots.
Surf trip planner: live 0-100 Strike Scores, 10-day forecasts, and trip picks for 1,100+ spots.
Related MCP Servers
- AlicenseAqualityBmaintenanceEnables users to check whether a beach suits a beach day or a surf session today or up to six days ahead, using Open-Meteo weather and marine forecasts scored by deterministic, documented rules. It exposes tools for raw hourly forecast data, suitability scores and verdicts by activity and skill level, and finding the best multi-hour window within a day.4MIT
- AlicenseAqualityBmaintenanceEnables AI agents to answer "should I go out on the water?" by blending Open-Meteo weather and marine forecasts with wind-sport logic. It finds rideable wind windows, rates sea state, compares spots, and returns go / marginal / no-go verdicts with explanations.61MIT
- AlicenseAqualityCmaintenanceProvides real-time water temperature and tide predictions for any lake, river, ocean, bay, or beach using NOAA, USGS, and other sources.173 PyPIMIT
- AlicenseAqualityDmaintenanceLive scuba diving planning for AI agents — ranked dive-forecast windows near any place for any day, best-time climatology per destination, marine-life seasonality from GBIF sightings, and facts for 4,800+ dive sites. Free and read-only; hosted at https://pickadive.com/mcp.5MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.