PickADive Scuba Diving
PickADive gives AI agents live and historical scuba-diving intelligence for 4,800+ dive sites worldwide.
Find dive windows — ranked favorable and moderate forecast windows near a place for a chosen day, with wave height, wind, timing, and site links.
Best time to dive — month-by-month climatology for a destination: historical favorability, water temperature, seas, and marine-life season windows.
Species seasonality — peak months and regional season windows for marquee species (e.g., whale sharks) from recorded sighting data.
Site facts — depths, difficulty, access, hazards, entry/exit notes, and certification level for named dive sites.
Top dive regions — world regions ranked by favorable dive windows over the next ~72 hours.
All results include source links, use metric unit-suffixed fields (wind in knots), and carry a safety disclaimer — forecasts are planning context, not safety clearance.
This server has a remotely hosted endpoint. Open its connector listing for connection details, authentication requirements, and setup instructions:
PickADive MCP Server
Live dive-conditions data for AI agents — forecast windows, best-time climatology, marine-life seasonality, and site facts for 4,800+ dive sites worldwide.
Hosted at https://pickadive.com/mcp — nothing to install
Setup · Tools · What you can do · Data & honesty · Security · Support
What can you do with it?
"Where can I dive near Boston this Saturday?" — ranked favorable and moderate forecast windows near any place for any day, with wave height, wind, timing, and site links.
"When should I book Komodo?" — month-by-month climatology for a destination: the share of days historically favorable, typical water temperature and seas, and marine-life season windows.
"When and where do whale sharks peak?" — species seasonality from 236k+ recorded GBIF sightings: peak month and regional season windows.
"How deep is Molasses Reef, and what are the hazards?" — public facts for any named dive site: depths, difficulty, shore/boat access, hazards, entry and exit notes.
"Where in the world is good for diving right now?" — regions ranked by favorable windows over the next ~72 hours.
Related MCP server: Scientific Tools MCP Server
Setup
Add the server to any MCP-compatible client — no key, no OAuth:
{
"mcpServers": {
"pickadive": { "url": "https://pickadive.com/mcp" }
}
}Client | How |
Claude Code |
|
Claude.ai / Desktop | Settings → Connectors → Add custom connector → |
Cursor · Windsurf · VS Code · Zed | Add the JSON block above to your MCP config |
Gemini CLI |
|
Local-only clients | Bridge with |
Discovery manifest: /.well-known/mcp.json ·
Agent onboarding: /llms.txt
Tools
Tool | Input | Output |
|
| Ranked windows: quality, |
|
| 12-month climatology + marine-life seasons + source page |
|
| Peak month, regional season windows, sighting counts |
|
| Depths, difficulty, access, hazards, entry/exit, cert level |
|
| World regions ranked by favorable windows (~72 h) |
All values are metric with unit-suffixed field names (max_depth_m,
wave_m, distance_km); wind is knots — the marine convention
everywhere. Tool descriptions instruct agents to convert for US users.
Every response includes a source link — please cite pickadive.com
when presenting results.
Data & honesty
Answers come from PickADive's own pipeline: hourly conditions gradings across 4,800+ curated dive sites (Open-Meteo marine + weather, NOAA tides), multi-year climatology, and 236k+ GBIF species sighting records.
Two rules the server never breaks:
Forecasts are planning context, never a safety clearance. Every response carries the disclaimer; agents should keep it.
Missing data is stated, never invented. Thin destinations return an honest "not enough history" rather than a guess.
Security
Read-only by design | No write tools — the server cannot create, modify, or delete anything. The worst a prompt injection can achieve through it is reading public dive data. |
No auth, no tokens, no user data | Nothing to leak, phish, or exfiltrate; connecting grants an agent no identity. |
Stateless JSON mode | One POST in, one JSON body out; no sessions, no server-push channel. |
HTTPS only, CORS open | Read-only public data. |
Transport & limits
Streamable HTTP (JSON-RPC 2.0 over POST), stateless — protocol versions
2024-11-05 → 2025-06-18.
Free for individual and assistant use at fair, non-bulk volumes; per-IP rate limiting applies. For sustained high-volume or commercial integrations, write to team@pickadive.com.
Example agent guidance (optional)
Add to your AGENTS.md / CLAUDE.md to reduce round-trips:
## PickADive MCP
- For "can I dive…?" questions use find_dive_windows with the user's
place; default day is Saturday.
- For trip planning use best_time_to_dive per destination; present
depths/waves in the user's customary units, keep wind in knots.
- Always keep the safety disclaimer and cite the linked page.Support & feedback
Issues, requests, corrections: team@pickadive.com
Documentation: pickadive.com/developers
The dataset behind the tools: pickadive.com/research · pickadive.com/trust
License
MIT — see LICENSE. The PickADive name and logo are trademarks of PickADive and are not covered by the code license.
Disclaimer
Dive conditions are graded forecasts — planning context only, never a safety judgment about any specific dive on any specific day. Always assess conditions at the water, dive within your training, and follow local guidance. Wildlife seasonality reflects recorded sightings, never a promise of encounters.
Available Tools
5 toolsbest_time_to_diveBest time of year to dive a destinationAInspect
Month-by-month climatology for ONE destination (country or famous destination like Komodo, Cozumel, Red Sea): share of days historically favorable, typical water temperature and seas, marine-life season windows. Historical patterns, never a forecast. Cite the linked page.
Inputs: destination (required).
find_dive_windowsFind dive windows near a placeAInspect
Ranked scuba-diving forecast windows near a place for a specific day. Answers "where can I dive near {place} on {day}?" with favorable and moderate windows (wave height, wind, timing) plus site links. Metric with unit-suffixed fields; wind_kn is knots. Convert depths/waves/distances for US users. Forecast planning context only — never a safety clearance. Always assess conditions at the water.
Inputs: day, lat, lng, near, +1 more.
site_factsFacts about a specific dive siteAInspect
Public facts for one named dive site: depths, difficulty, shore/boat access, hazards, entry and exit notes, and its page link. Metric with unit-suffixed fields.
Inputs: site (required).
species_seasonalityWhen and where a marine species peaksAInspect
Month-by-month seasonality for marquee dive species from recorded GBIF sightings: peak month and regional season windows. Recorded sightings, never a promise of encounters.
Inputs: species (required), lat, lng.
top_dive_regionsRegions with the best dive windows right nowAInspect
World regions ranked by favorable dive-forecast windows over the next ~72 hours. Forecast planning context only — never a safety clearance. Always assess conditions at the water.
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
Most tools are clearly distinguished by domain scope: forecasts vs. climatology vs. species seasonality vs. static site facts. Still, find_dive_windows and top_dive_regions both surface favorable forecast windows, and best_time_to_dive mentions marine-life seasonality that overlaps with species_seasonality, so slight boundary friction remains.
All names use readable lowercase snake_case, which gives the set a surface-level uniformity. However, the patterns are mixed: find_dive_windows is imperative while best_time_to_dive, top_dive_regions, species_seasonality, and site_facts are noun-phrase formulas rather than a consistent verb_noun convention.
At five tools, the server is well-scoped for its purpose. Each tool serves a distinct planning need without redundancy, and the count is comfortably within the ideal range for a focused domain.
The toolset covers short-term forecast windows, seasonal climatology, species timing, and site-level facts, which represents a strong dive-planning workflow. Minor gaps like per-site live condition updates or a tool for a broader trip plan can be worked around using the existing forecast and site data.
Maintenance
Related MCP Connectors
AI marketplace — flights, tours, activities, transport & more via MCP. No auth required.
Multi-tenant SaaS for dive, watersports, and outdoor activity operators. Manage trips, sessions, rosters, and bookings — tenant-isolated, OAuth 2.1 secured. Trip, roster, client and session tools for dive and watersports operators, scoped to one tenant. RidgeHQAPP MCP connects AI assistants to a multi-tenant booking platform for dive and watersports operators. Create/manage sessions, trips, rosters, and clients with tenant-scoped OAuth 2.1 or PAT auth — no destructive tool is ever exposed; writes require explicit confirmation.
Free public MCP for AI agents — 193 tools, 44 workflows. No API key.
Geocoding, routing, isochrones, traffic, weather, and place search for AI agents. 19 MCP tools.
Related MCP Servers
AlicenseAqualityDmaintenanceAI travel agent over MCP — live flights, hotels, activities, and events worldwide, then completes the booking on autonomad.ai.8188 npm2MIT- FlicenseAqualityDmaintenanceHigh-value scientific tools for AI agents — literature search (PubMed, arXiv, Semantic Scholar), chemical compound lookup (PubChem, ChEMBL), patent prior art search (USPTO, EPO), GPU spot prices across 4 providers, and real-time earth science data (USGS, NASA, OpenAQ). Per-call billing via API key. Keys issued instantly at https://mcp-site.com/keys/request6-
- AlicenseAqualityCmaintenanceUK planning application data for AI agents. Search, look up, and geo-query every UK planning application from Claude, Cursor, or any MCP client — conversationally.463 npmMIT
- AlicenseNot gradedqualityCmaintenanceProvides lake conditions, fish-stocking records, fishing-favorability scoring, and live weather for outdoor recreation AI agents, powering trip-planning and fishing apps with 72,000+ US lakes and 293,000+ stocking events.MIT