MCP App Store
by KeenEthics
Gillby icon

Gillby MCP Server for ChatGPT

By OneWave AI

Overview

Check Florida marine conditions, tides, wind, waves, hazards and source freshness. Plan boating trips, compare beaches, investigate fishing and dive conditions, and review water quality. Public marine data requires no account. Personal saved places, vessel profiles and trips require Gillby OAuth. Forecasts support personal judgment and do not replace official navigation charts.

How to connect

  1. ChatGPT: Open the Gillby listing in the ChatGPT app directory and choose Connect. ChatGPT listing Gillby exposes 120 tools here.

Tools

check_route_conditions

ChatGPT
Weather and marine conditions at up to five ordered spot IDs. Checks sampled stops only; does not create a navigable route or check depth, bridges, zones, or conditions between stops. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

compare_spots

ChatGPT
Compare current conditions for up to five verified comma-separated spot IDs. Partial failures remain explicit. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

delete_my_place

ChatGPT
Delete a saved place. Repeat deletes return deleted=false. Requires your Gillby account and explicit account consent. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

delete_my_trip

ChatGPT
Delete a saved trip. Repeat deletes return deleted=false. Requires your Gillby account and explicit account consent. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

find_anchorages

ChatGPT
Search published anchorages by name or west,south,east,north bbox. Verify access and operating details with the facility. Bridge data is published, not a live clearance calculation. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

find_beaches

ChatGPT
Search published beaches by name or west,south,east,north bbox. Verify access and operating details with the facility. Bridge data is published, not a live clearance calculation. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

find_boat_ramps

ChatGPT
Search published boat ramps by name or west,south,east,north bbox. Verify access and operating details with the facility. Bridge data is published, not a live clearance calculation. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

find_dive_sites

ChatGPT
Search published dive sites by name or west,south,east,north bbox. Verify access and operating details with the facility. Bridge data is published, not a live clearance calculation. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

find_fuel_docks

ChatGPT
Search published fuel docks by name or west,south,east,north bbox. Verify access and operating details with the facility. Bridge data is published, not a live clearance calculation. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

find_inlets

ChatGPT
Search published inlets by name or west,south,east,north bbox. Verify access and operating details with the facility. Bridge data is published, not a live clearance calculation. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

find_marinas

ChatGPT
Search published marinas by name or west,south,east,north bbox. Verify access and operating details with the facility. Bridge data is published, not a live clearance calculation. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

find_piers

ChatGPT
Search published piers by name or west,south,east,north bbox. Verify access and operating details with the facility. Bridge data is published, not a live clearance calculation. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

find_reefs

ChatGPT
Search published reefs by name or west,south,east,north bbox. Verify access and operating details with the facility. Bridge data is published, not a live clearance calculation. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

find_waterfront_dining

ChatGPT
Search published waterfront restaurants by name or west,south,east,north bbox. Verify access and operating details with the facility. Bridge data is published, not a live clearance calculation. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

find_wrecks

ChatGPT
Search published wrecks by name or west,south,east,north bbox. Verify access and operating details with the facility. Bridge data is published, not a live clearance calculation. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_activity_scores

ChatGPT
Hourly published activity scores with reasons and vetoes. Missing activity scores are unscored. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_air_temperature

ChatGPT
Air temperature for a verified spot over the next hours. Includes timestamp, source status and explicit nulls when unavailable. Water temperature is F; atmospheric visibility is mi, not underwater visibility; current sign follows the assigned station convention. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_algae_reports

ChatGPT
Reported algae samples from the published agency dataset, with source and availability. Empty reports do not establish safe conditions. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_beach_bacteria

ChatGPT
Beach bacteria samples for a verified spot. Preserve source sample dates and unavailable states. Satellite clarity is a relative index, not measured dive visibility. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_boat

ChatGPT
A single boat record from the library. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_briefing

ChatGPT
A short headline + <=60-word body written from the live data (numbers validated against the fact sheet; falls back to a template when no model is available). source says claude/openai/template. Rate limited: may call an LLM on a cold cache. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_california_coverage

ChatGPT
Explain California API/MCP beta coverage, sources and missing capabilities. Check before claiming Florida parity, continuous advisories or break-level surf scores. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_california_lake

ChatGPT
On-demand lake weather with wind/gusts kt, air F and source-dated gauge measurements. Preserve original elevation datum, units and provisional flags. Each measurement includes freshness independently; the gauge source uses the oldest returned parameter so a new temperature cannot conceal old level or flow. CDEC US/Pacific clock times are converted to UTC; any source clock without a verified offset has unknown freshness. No wave forecast or launch opening guarantee. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_california_protected_areas

ChatGPT
Paginated CDFW protected-area boundary geometry from a dated archive. Verify current CDFW fishing and access regulations; geometry alone does not establish permitted activities. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_california_river

ChatGPT
Get source-dated USGS river flow cfs, local gauge height ft and water temperature F where available, plus weather. Preserve measurement units and provisional flags; stage is not navigable depth. Each measurement includes independent freshness; sourceStatus separates retrieval and observation time and uses the oldest returned parameter. No navigation or water-contact safety rating. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_california_surf

ChatGPT
Get an on-demand California surf outlook for a forecastSupported spot ID from list_california_spots. Offshore swell ft/period s/directions FROM, wind kt/FROM, NOAA tide predictions ft MLLW and dated buoy observations. Offshore waves are not breaking-wave heights. Includes an experimental Gillby capped surf preference score (0–100), per-hour factors and model version. Missing essential inputs yield null. This is not a calibrated break-level surf rating; no beach advisory or shark-risk assessment is supplied. Includes parking guidance with checkedAt and official sources (availability null), localGuide where researched, exact NOAA tideEvents ft MLLW, dated NWS regional surf/rip-risk reports for supported Los Angeles spots, detailStatus with separate issues/retrieval time, and planning.days with morning/afternoon ranges in America/Los_Angeles. Null regional/localGuide means unavailable, not safe conditions. locationCameras matches the requested spot and supplies snapshotPath for refreshing JPEG previews, mediaType and unknown capture times; previews are not live video. cameras retains regional camera source links and provider-hosted YouTube IDs where available; these views may differ from the requested break and stream uptime is not guaranteed. Preserve issues and timestamps. sourceStatus distinguishes retrieval, observedAt, issuedAt (null when unknown), forecast validFrom/validThrough, current/stale/unavailable/unknown states, refreshAfterSec and maxObservationAgeSec (Gillby policies, not provider SLAs). Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_camera_image

ChatGPT
Fetch a public camera JPEG with source timestamp metadata for the Gillby panel. Returns image bytes through MCP, without a browser network request.

get_canal_discharges

ChatGPT
Canal discharge and freshwater releases from the published agency dataset, with source and availability. Empty reports do not establish safe conditions. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_chlorophyll

ChatGPT
Satellite chlorophyll and water color from the published agency dataset, with source and availability. Empty reports do not establish safe conditions. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_chop

ChatGPT
Boat ride and chop (use get_chop_history for past trends) for a verified spot over the next hours. Includes timestamp, source status and explicit nulls when unavailable. Water temperature is F; atmospheric visibility is mi, not underwater visibility; current sign follows the assigned station convention. For chop history or trends use get_chop_history with a verified spot ID. Preserve recorded versus reconstructed provenance, native 0–10 index and labels, coverage and gaps. Never invent assistant-defined rough/calm thresholds or silently substitute wave/wind series for native chop. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_chop_history

ChatGPT
Gillby's native 0-10 chop series: the latest 72 hours publicly, up to 31 days with a free Gillby account (OAuth sign-in); daily mean/max, coverage and 7-day trends. Recorded outputs and historical model reconstructions are identified separately. Never replace these with assistant-defined Calm/Moderate/Rough cutoffs or fabricate gaps. For chop history or trends use get_chop_history with a verified spot ID. Preserve recorded versus reconstructed provenance, native 0–10 index and labels, coverage and gaps. Never invent assistant-defined rough/calm thresholds or silently substitute wave/wind series for native chop. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_cloud_cover

ChatGPT
Cloud cover for a verified spot over the next hours. Includes timestamp, source status and explicit nulls when unavailable. Water temperature is F; atmospheric visibility is mi, not underwater visibility; current sign follows the assigned station convention. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_coastal_sensors

ChatGPT
SECOORA coastal sensor observations from the published agency dataset, with source and availability. Empty reports do not establish safe conditions. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_conditions

ChatGPT
The full conditions bundle for a named spot: current waves (ft, s, deg FROM), wind (kt), tide (ft MLLW), water temp (F), activity scores with reasons, 7-day hourly forecast, hi/lo tides, best windows, NWS alerts, rip/red tide/bacteria hazards, lightning and an AI briefing. Kitesurf: kiteboarding contains rider-specific weather screening and unverified launch status; supply kiteStyle, kiteExperience, kiteMinWindKt and kiteMaxWindKt. No overall kite score or verified launch is implied. Activities: kite, surf, skim (flatland), skim-wave (wave riding), paddle (flatwater paddleboard), sup-surf (SUP surf). Skim scores are absent without shoreline observations; do not substitute other activity scores. Prefer view=summary unless you need every hour. boat=<id> adds boat-specific chop comfort. For an arbitrary lat/lon use get_point_conditions. Start here for a current spot question with view=summary: this single result includes forecast, tides, scores, advisories, hazards, lightning and source status. Avoid duplicate hazard/tide calls unless a needed detail is absent. For beach questions, sea-model wave heights and NWS breaking-surf heights measure different things; their difference alone is not a forecast conflict. A swim no-go must not be followed by a recommendation to wade. Interpretation: omit boat unless the user supplied or confirmed it. Describe lightning as flashes observed or not detected in the stated window, never a clear/safe guarantee. Report unavailable/QC-failed sources even when freshness.stale=false; fresh does not mean every source is usable. Model sea height is not breaking surf height. Tide heights at different local MLLW gauges do not establish relative channel depths. High tide is not necessarily slack current. For kitesurfing use get_conditions with kiteStyle (freeride/waves/foil), kiteExperience and rider-supplied kiteMinWindKt/kiteMaxWindKt. Read kiteboarding for weather screening, gust spread and explicitly unverified launch status. Never infer the rider wind range, legal launch access or rescue coverage. Activity keys: kite, surf, skim (flatland), skim-wave (wave riding), paddle (flatwater paddleboard), sup-surf (SUP surf). Skim suitability is unscored without shoreline observations; missing scores must not inherit another activity. Offshore wind can favor surf while increasing paddleboard drift risk. A point depth cannot prove route clearance. Do not invent detection percentages, future readings, vessel ownership, or app settings instructions. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_coral_heat

ChatGPT
Coral heat stress and bleaching outlook from the published agency dataset, with source and availability. Empty reports do not establish safe conditions. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_currents

ChatGPT
Predicted inlet currents for a verified spot over the next hours. Includes timestamp, source status and explicit nulls when unavailable. Water temperature is F; atmospheric visibility is mi, not underwater visibility; current sign follows the assigned station convention. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_data_coverage

ChatGPT
Published dataset inventory and verified spot coverage; distinguishes unavailable data. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_dataset

ChatGPT
The latest payload of one dataset from list_datasets, including sharks and jellyfish. These marine-life records are dated observations, not live beach warnings; no records does not imply absence. bbox filters list datasets; category filters USCG notices (e.g. bridge,hazard); homeZone=true limits discharges to the home zone; geometry=true includes MPA polygons. 503 when the dataset has never loaded. Shark, jellyfish and man-of-war records are dated published observations, not live tracking, beach warnings, abundance estimates or swimming-safety scores. Preserve observation dates, uncertainty, attribution and source availability. No records does not mean the animals are absent. Source checked time is not observation time. Man-of-war are siphonophores, not true jellyfish. Local lifeguard links are not ingested current warnings; check the source report date. Never apply NOAA's Chesapeake sea-nettle forecast to Florida. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_departure_windows

ChatGPT
Published best windows filtered by activity. No windows means none were supplied, not a guarantee that every other hour is unsafe. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_depth

ChatGPT
Actual NOAA ENC chart depth and optional DEM depth at a Florida coordinate, with charted hazards, channel context and restriction zones. A point check does not prove clearance along a route. Interpretation: omit boat unless the user supplied or confirmed it. Describe lightning as flashes observed or not detected in the stated window, never a clear/safe guarantee. Report unavailable/QC-failed sources even when freshness.stale=false; fresh does not mean every source is usable. Model sea height is not breaking surf height. Tide heights at different local MLLW gauges do not establish relative channel depths. High tide is not necessarily slack current. For kitesurfing use get_conditions with kiteStyle (freeride/waves/foil), kiteExperience and rider-supplied kiteMinWindKt/kiteMaxWindKt. Read kiteboarding for weather screening, gust spread and explicitly unverified launch status. Never infer the rider wind range, legal launch access or rescue coverage. Activity keys: kite, surf, skim (flatland), skim-wave (wave riding), paddle (flatwater paddleboard), sup-surf (SUP surf). Skim suitability is unscored without shoreline observations; missing scores must not inherit another activity. Offshore wind can favor surf while increasing paddleboard drift risk. A point depth cannot prove route clearance. Do not invent detection percentages, future readings, vessel ownership, or app settings instructions. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_derelict_vessels

ChatGPT
Reported derelict vessels from the published agency dataset, with source and availability. Empty reports do not establish safe conditions. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_fish_kills

ChatGPT
Reported fish kills from the published agency dataset, with source and availability. Empty reports do not establish safe conditions. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_fishing_heatmap

ChatGPT
Published Florida mahi, blue/white marlin, tarpon and snook evidence: dated NOAA commercial catches and research/community occurrences, source/license credits, coordinate uncertainty, seasonal record counts and configurable 0.25/0.10/0.05/0.02/0.01/0.005-degree heatmap cells. Historical records are not live fish locations, migration tracks, abundance, catch rates or catch probabilities. Sampling/fishing effort is uncorrected; absent records do not establish fish absence. from/to are inclusive YYYY-MM-DD observation dates; month pools all selected years. Source check time is not observation time. Recency weighting defaults to recent: exponential 365-day half-life based on observation dates, not source retrieval. weighting=historical gives equal weights. No upstream downloads on tool calls. Preserve species, observation dates, source credits, coordinate uncertainty, query coverage, partial/stale flags and fishing-effort bias. Heatmap color is record density, never fish abundance or catch odds. Commercial catches and occurrences must remain distinguishable. No generated migration paths. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_fishing_insights

ChatGPT
Published Florida mahi, blue/white marlin, tarpon and snook evidence: dated NOAA commercial catches and research/community occurrences, source/license credits, coordinate uncertainty, seasonal record counts and configurable 0.25/0.10/0.05/0.02/0.01/0.005-degree heatmap cells. Historical records are not live fish locations, migration tracks, abundance, catch rates or catch probabilities. Sampling/fishing effort is uncorrected; absent records do not establish fish absence. from/to are inclusive YYYY-MM-DD observation dates; month pools all selected years. Source check time is not observation time. Recency weighting defaults to recent: exponential 365-day half-life based on observation dates, not source retrieval. weighting=historical gives equal weights. No upstream downloads on tool calls. Preserve species, observation dates, source credits, coordinate uncertainty, query coverage, partial/stale flags and fishing-effort bias. Heatmap color is record density, never fish abundance or catch odds. Commercial catches and occurrences must remain distinguishable. No generated migration paths. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_fishing_records

ChatGPT
Published Florida mahi, blue/white marlin, tarpon and snook evidence: dated NOAA commercial catches and research/community occurrences, source/license credits, coordinate uncertainty, seasonal record counts and configurable 0.25/0.10/0.05/0.02/0.01/0.005-degree heatmap cells. Historical records are not live fish locations, migration tracks, abundance, catch rates or catch probabilities. Sampling/fishing effort is uncorrected; absent records do not establish fish absence. from/to are inclusive YYYY-MM-DD observation dates; month pools all selected years. Source check time is not observation time. Recency weighting defaults to recent: exponential 365-day half-life based on observation dates, not source retrieval. weighting=historical gives equal weights. No upstream downloads on tool calls. Preserve species, observation dates, source credits, coordinate uncertainty, query coverage, partial/stale flags and fishing-effort bias. Heatmap color is record density, never fish abundance or catch odds. Commercial catches and occurrences must remain distinguishable. No generated migration paths. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_florida_lakes

ChatGPT
Florida USGS lake monitoring inventory, levels with original vertical datum, temperature and storage where measured; historical stations and stale readings identified from the published agency dataset, with source and availability. Empty reports do not establish safe conditions. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_florida_rivers

ChatGPT
Florida NOAA river and water gauges, observed readings and separate forecast summaries from the published agency dataset, with source and availability. Empty reports do not establish safe conditions. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_forecast

ChatGPT
Hourly forecast for a spot (or lat+lon) starting at time (default now) for hours hours: waves, swell/wind-wave split, wind, gusts, tide, current, precip/thunder chance, and go/caution/nogo scores with reasons per activity. Also returns 7 daily score rows and best windows. Units: ft, s, kt, deg FROM, F. Use one call per spot for a time-window comparison; request only the hours needed. Hourly rows include tide/current and score reasons. Do not infer one inlet has deeper water by comparing local tide heights. Interpretation: omit boat unless the user supplied or confirmed it. Describe lightning as flashes observed or not detected in the stated window, never a clear/safe guarantee. Report unavailable/QC-failed sources even when freshness.stale=false; fresh does not mean every source is usable. Model sea height is not breaking surf height. Tide heights at different local MLLW gauges do not establish relative channel depths. High tide is not necessarily slack current. For kitesurfing use get_conditions with kiteStyle (freeride/waves/foil), kiteExperience and rider-supplied kiteMinWindKt/kiteMaxWindKt. Read kiteboarding for weather screening, gust spread and explicitly unverified launch status. Never infer the rider wind range, legal launch access or rescue coverage. Activity keys: kite, surf, skim (flatland), skim-wave (wave riding), paddle (flatwater paddleboard), sup-surf (SUP surf). Skim suitability is unscored without shoreline observations; missing scores must not inherit another activity. Offshore wind can favor surf while increasing paddleboard drift risk. A point depth cannot prove route clearance. Do not invent detection percentages, future readings, vessel ownership, or app settings instructions. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_gulf_stream

ChatGPT
Approximate Gulf Stream edge for a verified spot. Preserve source sample dates and unavailable states. Satellite clarity is a relative index, not measured dive visibility. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_hazards

ChatGPT
Active NWS marine/coastal alerts (small craft, rip current, high surf, special marine, waterspout...) plus water hazards for a spot or lat+lon: rip current risk, red tide (FWC samples), bacteria (FDOH), sargassum, water clarity, king tide, Gulf Stream distance, lightning. Use before recommending swimming, diving or running an inlet. Interpretation: omit boat unless the user supplied or confirmed it. Describe lightning as flashes observed or not detected in the stated window, never a clear/safe guarantee. Report unavailable/QC-failed sources even when freshness.stale=false; fresh does not mean every source is usable. Model sea height is not breaking surf height. Tide heights at different local MLLW gauges do not establish relative channel depths. High tide is not necessarily slack current. For kitesurfing use get_conditions with kiteStyle (freeride/waves/foil), kiteExperience and rider-supplied kiteMinWindKt/kiteMaxWindKt. Read kiteboarding for weather screening, gust spread and explicitly unverified launch status. Never infer the rider wind range, legal launch access or rescue coverage. Activity keys: kite, surf, skim (flatland), skim-wave (wave riding), paddle (flatwater paddleboard), sup-surf (SUP surf). Skim suitability is unscored without shoreline observations; missing scores must not inherit another activity. Offshore wind can favor surf while increasing paddleboard drift risk. A point depth cannot prove route clearance. Do not invent detection percentages, future readings, vessel ownership, or app settings instructions. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_health

ChatGPT
Rolls up whether the ingest worker is running, which feed families (ndbc, coops, nws, openmeteo, goes19, coastwatch...) have stale sources, government dataset status and the GLM lightning feed. status is ok | degraded | down; HTTP 503 only when down. Check this before trusting 'no data' from other tools. detail=true lists every source. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_history

ChatGPT
Read stored observations or forecast history for source and var. Forecast source uses forecast:model and requires spot. Public access covers the latest 72 hours; a free Gillby account (OAuth sign-in) allows windows up to 31 days; up to 1000 points. Latest revision/run wins. Rejected and suspect rows are excluded; unreviewed rows retain quality metadata. For chop history or trends use get_chop_history with a verified spot ID. Preserve recorded versus reconstructed provenance, native 0–10 index and labels, coverage and gaps. Never invent assistant-defined rough/calm thresholds or silently substitute wave/wind series for native chop. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_hurricane_history

ChatGPT
Search 26 completed seasons of NOAA NHC HURDAT2 best-track history (2000–2025), Atlantic and eastern/central Pacific. Includes tropical cyclones, not only hurricanes. Filter by basin, year range, name, storm ID, hurricane strength or recorded landfall. Paginated summaries by default; includeTrack=true returns UTC positions, sustained wind kt, pressure mb, status, special-event flags and 34/50/64 kt wind radii in nautical miles ordered NE, SE, SW, NW. Missing measurements are null. Landfall flags cover any coastline, not specifically the US. Finalized retrospective tracks are not forecasts; current 2026 advisories use get_hurricanes. Historical tracks alone do not measure local damage or future risk. Units: sustained wind kt; pressure mb; coordinates degrees; UTC track timestamps; wind radii nautical miles ordered NE, SE, SW, NW. Missing measurements are null. Returns data and source/freshness metadata.

get_hurricanes

ChatGPT
Active NHC tropical cyclones in the Atlantic and eastern/central Pacific. Returns position, maximum sustained wind (kt), pressure (mb), movement (degrees toward and kt), advisory timestamps and official advisory/forecast/cone links. Preserve stale/unavailable status. An empty active-storm list does not rule out developing systems or local hazards. The cone is not an impact boundary. Follow official local warnings. Units: sustained wind and movement speed kt; pressure mb; coordinates degrees; movement bearings TOWARD. Advisory and retrieval timestamps are separate. Returns data and source/freshness metadata.

get_jellyfish_observations

ChatGPT
Published Florida jellyfish, box jellyfish and man-of-war observations from OBIS and iNaturalist, with observation dates, uncertainty, observer credits and licenses. Includes official Boca Raton/Fort Lauderdale lifeguard-report links. Community records are not live beach warnings; no sightings does not establish absence. Man-of-war are siphonophores. Use bbox to narrow the sample; limit defaults to 20 (maximum 100). Shark, jellyfish and man-of-war records are dated published observations, not live tracking, beach warnings, abundance estimates or swimming-safety scores. Preserve observation dates, uncertainty, attribution and source availability. No records does not mean the animals are absent. Source checked time is not observation time. Man-of-war are siphonophores, not true jellyfish. Local lifeguard links are not ingested current warnings; check the source report date. Never apply NOAA's Chesapeake sea-nettle forecast to Florida. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_king_tide

ChatGPT
King tide forecast for a verified spot. Preserve source sample dates and unavailable states. Satellite clarity is a relative index, not measured dive visibility. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_lake_okeechobee

ChatGPT
Lake Okeechobee stage and releases from the published agency dataset, with source and availability. Empty reports do not establish safe conditions. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_lightning

ChatGPT
GOES-19 GLM lightning. With lat+lon: level (clear | watch 10-25 mi | danger < 10 mi in the last 5 min), nearest strike distance (mi) and time, strikes in 15 min, all-clear time (30 min after the last strike within 10 mi), SPC thunder outlook, and the last 30 min of flashes. Without lat/lon: status per spot. When the feed is stale, status is null and unavailableReason explains why (never a false 'clear'). Prefer list_spots for named spot coordinates. State no flashes detected in the observed window rather than no lightning exists. Stale/incomplete coverage means unknown. Do not supply detection rates that are absent from this result. Interpretation: omit boat unless the user supplied or confirmed it. Describe lightning as flashes observed or not detected in the stated window, never a clear/safe guarantee. Report unavailable/QC-failed sources even when freshness.stale=false; fresh does not mean every source is usable. Model sea height is not breaking surf height. Tide heights at different local MLLW gauges do not establish relative channel depths. High tide is not necessarily slack current. For kitesurfing use get_conditions with kiteStyle (freeride/waves/foil), kiteExperience and rider-supplied kiteMinWindKt/kiteMaxWindKt. Read kiteboarding for weather screening, gust spread and explicitly unverified launch status. Never infer the rider wind range, legal launch access or rescue coverage. Activity keys: kite, surf, skim (flatland), skim-wave (wave riding), paddle (flatwater paddleboard), sup-surf (SUP surf). Skim suitability is unscored without shoreline observations; missing scores must not inherit another activity. Offshore wind can favor surf while increasing paddleboard drift risk. A point depth cannot prove route clearance. Do not invent detection percentages, future readings, vessel ownership, or app settings instructions. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_marine_alerts

ChatGPT
Active and upcoming alerts for a spot, retaining start/end times and source links. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_my_notification_settings

ChatGPT
Read notification preferences and actual delivery availability. Requires your Gillby account and explicit account consent. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_my_place

ChatGPT
Read one saved place. Requires your Gillby account and explicit account consent. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_my_settings

ChatGPT
Read saved vessel, preferences and notification settings. Missing vessel measurements remain null. Requires your Gillby account and explicit account consent. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_my_trip

ChatGPT
Read one saved trip. Requires your Gillby account and explicit account consent. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_my_vessel

ChatGPT
Requires OAuth login to your Gillby account. Reads only your saved vessel and route clearance settings. No writes and no other account access. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_navigation_notices

ChatGPT
USCG local notices to mariners from the published agency dataset, with source and availability. Empty reports do not establish safe conditions. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_observations

ChatGPT
Actual buoy and station observations for a spot with timestamps. These may differ from blended forecast conditions. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_park_alerts

ChatGPT
Coastal national park alerts and closures from the published agency dataset, with source and availability. Empty reports do not establish safe conditions. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_parking_guides

ChatGPT
Discover checked Florida or California launch/trailer and beach parking guides. Supply state, optionally an exact guide ID; omit id to list available guides and IDs. Returns official sources, checkedAt (research date, not publication time), entrance directions when researched, permit/fee/access guidance, construction notices and published capacity where supplied. Coverage is selected locations, not every launch. Unknown IDs return no guide. availability is always null: no live occupancy, opening or reopening feed is connected. Never substitute ordinary car-lot parking for trailer permission. Facility inventory is available through get_poi_details for supported Florida POI IDs. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_poi

ChatGPT
Look up a published coastal POI by its exact ID. Does not refresh facility details or calculate live bridge clearance. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_poi_details

ChatGPT
Read source-linked details for a published Florida boat ramp, marina, fuel dock or waterfront restaurant by exact POI ID returned by a place search. Includes contact details, parking trailer/car/accessible space counts where published, hours, fees, slips, amenities and per-field sources/dates. Launch parking includes 84 collected FWC records and checked operator guidance at selected facilities; launch:notice facts may describe construction or closure and take priority over routine hours/rates. Published capacity is not live availability. Preserve unknown values, source dates and conflicting records. Does not establish current ramp reopening, trailer permission, dock access, live fuel prices or navigable depth. California directory IDs use list_california_facilities; use get_parking_guides for checked California parking guidance. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_point_conditions

ChatGPT
Same bundle as get_conditions for an arbitrary point inside Florida coverage, including the Keys and Everglades. Model cache points round to 0.02 deg; station references are used only near configured spots. Hosted cold pins request worker publication and return 503 with Retry-After while pending; retry the same coordinate. Source times and coverage remain explicit. Returns 422 unprocessable when the point is on land (details.nearestSpot suggests a spot). Cold point processing can take longer than a named-spot read. Rate limited. Start here for a current spot question with view=summary: this single result includes forecast, tides, scores, advisories, hazards, lightning and source status. Avoid duplicate hazard/tide calls unless a needed detail is absent. For beach questions, sea-model wave heights and NWS breaking-surf heights measure different things; their difference alone is not a forecast conflict. A swim no-go must not be followed by a recommendation to wade. Interpretation: omit boat unless the user supplied or confirmed it. Describe lightning as flashes observed or not detected in the stated window, never a clear/safe guarantee. Report unavailable/QC-failed sources even when freshness.stale=false; fresh does not mean every source is usable. Model sea height is not breaking surf height. Tide heights at different local MLLW gauges do not establish relative channel depths. High tide is not necessarily slack current. For kitesurfing use get_conditions with kiteStyle (freeride/waves/foil), kiteExperience and rider-supplied kiteMinWindKt/kiteMaxWindKt. Read kiteboarding for weather screening, gust spread and explicitly unverified launch status. Never infer the rider wind range, legal launch access or rescue coverage. Activity keys: kite, surf, skim (flatland), skim-wave (wave riding), paddle (flatwater paddleboard), sup-surf (SUP surf). Skim suitability is unscored without shoreline observations; missing scores must not inherit another activity. Offshore wind can favor surf while increasing paddleboard drift risk. A point depth cannot prove route clearance. Do not invent detection percentages, future readings, vessel ownership, or app settings instructions. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_pollution_notices

ChatGPT
Pollution incident notices from the published agency dataset, with source and availability. Empty reports do not establish safe conditions. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_pressure

ChatGPT
Air pressure for a verified spot over the next hours. Includes timestamp, source status and explicit nulls when unavailable. Water temperature is F; atmospheric visibility is mi, not underwater visibility; current sign follows the assigned station convention. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_protected_areas

ChatGPT
Marine protected areas from the published agency dataset, with source and availability. Empty reports do not establish safe conditions. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_rain

ChatGPT
Rain probability and accumulation for a verified spot over the next hours. Includes timestamp, source status and explicit nulls when unavailable. Water temperature is F; atmospheric visibility is mi, not underwater visibility; current sign follows the assigned station convention. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_rainfall_history

ChatGPT
Observed daily precipitation from NOAA NCEI GHCN-Daily at one of six selected Florida airport stations, not archived forecasts. Required station, start and end (YYYY-MM-DD); completed dates only, 1900 onward, at most 366 inclusive days per request. Public, no API key. Returns daily values in inches, original flags, coverage, monthly summaries and totals. totalIn is null for incomplete coverage; partialTotalIn is only the sum of accepted reported values. Trace is not dry. Presumed-zero, incomplete-period and quality-flagged reports are excluded. Reporting dates are station climate days, not UTC hours. A station does not measure rainfall at a nearby beach, inlet or across a region. Recent records may lag or be revised. Use for how much precipitation fell: NOAA observed station records, not forecast archives. Preserve station, reporting dates, trace days, missing/excluded counts and coverage. Never present partialTotalIn as a complete monthly/yearly total. Station rainfall is not an area-wide measurement. Use get_rain for future amounts and get_history source=forecast:om_weather_best var=precip_in only for archived model estimates. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_red_tide

ChatGPT
Red tide samples for a verified spot. Preserve source sample dates and unavailable states. Satellite clarity is a relative index, not measured dive visibility. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_release_updates

ChatGPT
Read the current Gillby release version, date, supported MCP protocol and dated changes shared by the API and MCP. API URL versions are separate from product release versions. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_rip_risk

ChatGPT
Rip current risk for a verified spot. Preserve source sample dates and unavailable states. Satellite clarity is a relative index, not measured dive visibility. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_sargassum

ChatGPT
Local sargassum risk for a verified spot. Preserve source sample dates and unavailable states. Satellite clarity is a relative index, not measured dive visibility. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_sargassum_outlook

ChatGPT
Sargassum research product availability from the published agency dataset, with source and availability. Empty reports do not establish safe conditions. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_shark_research

ChatGPT
Published Florida shark research occurrences with observation dates, location uncertainty, source credits and licenses. Historical acoustic detections and tag releases, not live shark tracking or beach warnings. No records does not mean sharks are absent. Use bbox to narrow the published sample; limit defaults to 20 (maximum 100). Shark, jellyfish and man-of-war records are dated published observations, not live tracking, beach warnings, abundance estimates or swimming-safety scores. Preserve observation dates, uncertainty, attribution and source availability. No records does not mean the animals are absent. Source checked time is not observation time. Man-of-war are siphonophores, not true jellyfish. Local lifeguard links are not ingested current warnings; check the source report date. Never apply NOAA's Chesapeake sea-nettle forecast to Florida. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_source_status

ChatGPT
Fresh, stale, unavailable and QC-rejected sources used by spot conditions. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_southeast_lakes

ChatGPT
Georgia, South Carolina and North Carolina reservoir levels: Lanier, Allatoona, West Point, Hartwell, Russell, Thurmond/Clarks Hill, Oconee, Sinclair, Seminole, Murray, Marion, Moultrie, Wateree, Keowee, Jocassee, Wylie, Norman, Jordan, Falls, Kerr, Gaston, High Rock, Badin, James, Fontana and Hickory. USGS lake elevation keeps its original datum (NGVD29, NAVD88 or station datum); NWPS pool levels for Duke Energy lakes are project-relative (near 100 ft at full pond), not sea-level elevations. Lakes with no current gauge stay listed with reporting=false and a reason. Optional state=GA|SC|NC and bbox filters. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_southeast_rivers

ChatGPT
Georgia, South Carolina and North Carolina river gauges for fishing and paddling: Cape Fear, Neuse, Tar/Pamlico, Roanoke, Waccamaw, Lumber, Pee Dee, Santee, Cooper, Edisto, Ashley, Congaree, Saluda, Broad, Savannah, Ogeechee, Altamaha, Ocmulgee, Oconee, Satilla, St. Marys, Chattahoochee, Etowah, French Broad, Nantahala, Catawba and Yadkin. USGS gauge height (local gauge datum, not depth), discharge and water temperature, plus the NWS flood category and a separate forecast summary where NWPS publishes one. Tidal gauges are flagged. Gauges that are not reporting stay listed with reporting=false. Optional state=GA|SC|NC and bbox filters. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_spot

ChatGPT
A single spot record plus now.scores (go/caution/nogo per activity for the current hour) when the worker has scored it. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_surf_forecast

ChatGPT
NWS surf zone forecast for a verified spot. Preserve source sample dates and unavailable states. Satellite clarity is a relative index, not measured dive visibility. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_temperature_fronts

ChatGPT
Satellite sea temperature fronts from the published agency dataset, with source and availability. Empty reports do not establish safe conditions. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_thunder_forecast

ChatGPT
Thunderstorm forecast for a verified spot over the next hours. Includes timestamp, source status and explicit nulls when unavailable. Water temperature is F; atmospheric visibility is mi, not underwater visibility; current sign follows the assigned station convention. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_tides

ChatGPT
Predicted high and low tides (ft above MLLW, NOAA CO-OPS) for the next days days at a spot or lat+lon, the hourly tide height curve and inlet current (kt, + flood / - ebb), plus sunrise/sunset and moon phase. Times are ISO with the Eastern offset. Interpretation: omit boat unless the user supplied or confirmed it. Describe lightning as flashes observed or not detected in the stated window, never a clear/safe guarantee. Report unavailable/QC-failed sources even when freshness.stale=false; fresh does not mean every source is usable. Model sea height is not breaking surf height. Tide heights at different local MLLW gauges do not establish relative channel depths. High tide is not necessarily slack current. For kitesurfing use get_conditions with kiteStyle (freeride/waves/foil), kiteExperience and rider-supplied kiteMinWindKt/kiteMaxWindKt. Read kiteboarding for weather screening, gust spread and explicitly unverified launch status. Never infer the rider wind range, legal launch access or rescue coverage. Activity keys: kite, surf, skim (flatland), skim-wave (wave riding), paddle (flatwater paddleboard), sup-surf (SUP surf). Skim suitability is unscored without shoreline observations; missing scores must not inherit another activity. Offshore wind can favor surf while increasing paddleboard drift risk. A point depth cannot prove route clearance. Do not invent detection percentages, future readings, vessel ownership, or app settings instructions. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_usgs_water

ChatGPT
USGS flow, salinity and water temperature from the published agency dataset, with source and availability. Empty reports do not establish safe conditions. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_uv_forecast

ChatGPT
UV forecast for a verified spot over the next hours. Includes timestamp, source status and explicit nulls when unavailable. Water temperature is F; atmospheric visibility is mi, not underwater visibility; current sign follows the assigned station convention. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_visibility

ChatGPT
Atmospheric visibility for a verified spot over the next hours. Includes timestamp, source status and explicit nulls when unavailable. Water temperature is F; atmospheric visibility is mi, not underwater visibility; current sign follows the assigned station convention. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_water_clarity

ChatGPT
Satellite water clarity for a verified spot. Preserve source sample dates and unavailable states. Satellite clarity is a relative index, not measured dive visibility. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_water_temperature

ChatGPT
Water temperature for a verified spot over the next hours. Includes timestamp, source status and explicit nulls when unavailable. Water temperature is F; atmospheric visibility is mi, not underwater visibility; current sign follows the assigned station convention. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_wave_models

ChatGPT
Published wave-model series and model spread for a spot; absent models stay unavailable. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_waves

ChatGPT
Wave height, period and swell for a verified spot over the next hours. Includes timestamp, source status and explicit nulls when unavailable. Water temperature is F; atmospheric visibility is mi, not underwater visibility; current sign follows the assigned station convention. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

get_wind

ChatGPT
Wind and gusts for a verified spot over the next hours. Includes timestamp, source status and explicit nulls when unavailable. Water temperature is F; atmospheric visibility is mi, not underwater visibility; current sign follows the assigned station convention. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

list_boats

ChatGPT
Boats with published specs (LOA, beam, draft, deadrise, weight, hull type, fuel, cruise speed) and their sources. Pass a boat id to conditions/forecast/routes for boat-specific comfort and draft. The user's boat is contender-21-open-2008. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

list_bridges

ChatGPT
Search published bridges by name or west,south,east,north bbox. Verify access and operating details with the facility. Bridge data is published, not a live clearance calculation. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

list_california_facilities

ChatGPT
Paginated dated State Parks boating-facility source records. Unverified facilities have no map coordinates; opening/access and amenities require operator confirmation. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

list_california_lakes

ChatGPT
List California lake IDs, model point coordinates and gauge references. Lake centers are approximate, not surveyed launches. Use get_california_lake for weather and gauge data. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

list_california_places

ChatGPT
Browse dated California station, access and port source records from a packaged archive. This is historical source data, not continuous live conditions. Times on observations may precede archive download time. No current beach-advisory status. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

list_california_rivers

ChatGPT
List configured California river gauge IDs and source references. Use get_california_river for observations and local forecast; stage is local gauge height, not navigation depth. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

list_california_spots

ChatGPT
List California surf locations with source links, coordinate roles and forecastSupported flags. Includes 10 configured locations plus coordinate-based model outlooks for official surfing-access, historical and community listings; overlapping source records are not a unique verified surf-break count. Pagination uses offset/limit. Use a forecastSupported ID with get_california_surf. Directory locations have no verified beach orientation or preference score. Preserve model limitations and source gaps. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

list_cams

ChatGPT
Live source links and credits near a spot or coordinate; archived imagery may be unavailable. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

list_datasets

ChatGPT
Index of government datasets (SFWMD discharges, Lake O, USGS, CoastWatch chlorophyll / SST fronts, coral heat, USCG notices, derelicts, MPAs, algae, fish kills, shark research and jellyfish/man-of-war observations) with ok/stale/unavailable status and last-good time. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

list_my_places

ChatGPT
Read your saved places and favorites. Requires your Gillby account and explicit account consent. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

list_my_trips

ChatGPT
Read your saved trips. Requires your Gillby account and explicit account consent. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

list_sandbars

ChatGPT
Search published sandbars by name or west,south,east,north bbox. Verify access and operating details with the facility. Bridge data is published, not a live clearance calculation. For a named recreational/scored spot such as Lake Boca Sandbar, use list_spots first to get verified coordinates and IDs. This search is for places absent from the spot catalog; avoid repeated searches for an already cataloged spot. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

list_spots

ChatGPT
Every named South Florida spot the app scores, with its lat/lon, kind, region and the NOAA stations used for it. Use the returned id with conditions, forecast, tides, hazards and briefing tools. include=status adds the current-hour go/caution/nogo band per activity. Use this for a map of verified coastal spots: the MCP app panel renders an interactive Florida map with selectable spots, nearby camera markers and conditions. Coordinates are geographic locations, not safe navigation routes. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

plan_my_route

ChatGPT
Requires OAuth login. Uses your saved vessel, draft, air draft, speed, under-keel and bridge margins for actual chart routing. Explicit measurements override saved values. Never guesses missing required measurements. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

plan_route

ChatGPT
Requires a free Gillby account (OAuth sign-in). Chart-aware water routing between from/to spot IDs or lat,lon. Supply a confirmed library boat ID or measured draft, with beam, airDraft, ukc, bridgeMargin and speed overrides in feet/knots. Checks chart depths and tides along the geometry, samples across supplied beam, identifies bridges and restrictions, checks predicted MHW bridge clearance when data permits, and adds route weather samples. Does not infer saved vessel settings. Supports ordered via stops and a hard corridor=icw constraint. Cold charts may take 110 seconds. Interpretation: omit boat unless the user supplied or confirmed it. Describe lightning as flashes observed or not detected in the stated window, never a clear/safe guarantee. Report unavailable/QC-failed sources even when freshness.stale=false; fresh does not mean every source is usable. Model sea height is not breaking surf height. Tide heights at different local MLLW gauges do not establish relative channel depths. High tide is not necessarily slack current. For kitesurfing use get_conditions with kiteStyle (freeride/waves/foil), kiteExperience and rider-supplied kiteMinWindKt/kiteMaxWindKt. Read kiteboarding for weather screening, gust spread and explicitly unverified launch status. Never infer the rider wind range, legal launch access or rescue coverage. Activity keys: kite, surf, skim (flatland), skim-wave (wave riding), paddle (flatwater paddleboard), sup-surf (SUP surf). Skim suitability is unscored without shoreline observations; missing scores must not inherit another activity. Offshore wind can favor surf while increasing paddleboard drift risk. A point depth cannot prove route clearance. Do not invent detection percentages, future readings, vessel ownership, or app settings instructions. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

save_my_place

ChatGPT
Save a place or favorite. Supply a unique requestId and reuse it when retrying the same save; reused IDs with different input are rejected. Requires your Gillby account and explicit account consent. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

save_my_trip

ChatGPT
Save a trip. Supply a unique requestId and reuse it on retry. Saving does not assess navigation safety. Requires your Gillby account and explicit account consent. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

search_pois

ChatGPT
Search public marine POIs. Optional cats is a comma-separated category list. Fuel prices and current bridge clearance are not verified. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

update_my_notification_settings

ChatGPT
Save notification preferences. Hosted delivery is in-app only; this does not enable push, email or notifications on this AI client. Requires your Gillby account and explicit account consent. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

update_my_place

ChatGPT
Update specified saved-place fields. Requires your Gillby account and explicit account consent. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

update_my_settings

ChatGPT
Update only specified vessel or preference fields. Requires your Gillby account and explicit account consent. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

update_my_trip

ChatGPT
Update specified trip fields; this does not recheck route safety. Requires your Gillby account and explicit account consent. Units: ft, kt, s, F, mi; directions FROM. Returns data and source/freshness metadata.

Capabilities

WritesInteractive

Example Prompts

Click any prompt to copy it.

Similar Apps

Listed on MCP App Store

Listed on MCP App Store

Add this badge to your site or README. It links to this page.

HTML

<a href="https://mcp-app-store.keenethics-labs.com/app/gillby"><img src="https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg" alt="Listed on MCP App Store" width="220" height="44"></a>

Markdown

[![Listed on MCP App Store](https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg)](https://mcp-app-store.keenethics-labs.com/app/gillby)