Plans scuba dives with live forecast windows, climatology, species seasons, and facts for 4,800+ global sites.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent β or use 1-click editor setup below.
π‘ Paste the JSON block into your client's configuration file under mcpServers, then restart the application.
Inspect callable tools, capabilities, and parameters exposed to AI agents by PickADive Scuba Diving.
find_dive_windowslat+lng, day?, radius_km?}
best_time_to_dive12-month climatology + marine-life seasons + source page
species_seasonalityPeak month, regional season windows, sighting counts
site_factsDepths, difficulty, access, hazards, entry/exit, cert level
top_dive_regionsWorld regions ranked by favorable windows (~72 h)
PickADive Scuba Diving gives AI agents read-only access to scuba-diving planning data from PickADive. Its coverage includes more than 4,800 curated dive sites and combines forecast conditions, historical patterns, marine-life records, and public site information.
The server can help answer questions such as where conditions may be favorable near a location on a given day, which months are typically better for a destination, when a species is most frequently recorded in a region, and what is known about a named dive site. It is intended for planning and research, not for deciding whether a particular dive is safe.
The service is hosted at https://pickadive.com/mcp and uses Streamable HTTP with JSON-RPC over POST. Requests are stateless: a client sends a request and receives a JSON response without a session or server-push channel. No authentication, token, or user identity is required.
Forecast information is generated from PickADiveβs pipeline, including hourly condition grading across its dive sites, Open-Meteo marine and weather data, and NOAA tides. Historical destination guidance uses multi-year climatology. Species results draw on more than 236,000 recorded GBIF sightings.
Responses use metric units with unit-bearing field names such as wave_m, max_depth_m, and distance_km; wind is reported in knots. Results include a source link, and agents should preserve the stated safety disclaimer when presenting forecast information. When the available history is too limited, the service reports that limitation instead of filling the gap with an estimate.
Add the hosted endpoint to an MCP-compatible client with a server entry such as:
Claude Code and Gemini CLI can add the endpoint with their HTTP MCP commands. Claude.ai or Desktop supports adding it as a custom connector. Cursor, Windsurf, VS Code, and Zed can use the same JSON configuration. Clients that only support local processes can use npx mcp-remote https://pickadive.com/mcp as a bridge.
The service is free for individual and assistant use at fair, non-bulk volumes. Per-IP rate limits apply, and sustained high-volume or commercial use should be discussed with PickADive. There are no environment variables or credentials required by the hosted endpoint.
PickADive Scuba Diving exposes five read-only tools:
find_dive_windows accepts a place or latitude and longitude, with optional day and search radius, and returns ranked favorable or moderate windows with wave height, wind, timing, and site links.best_time_to_dive accepts a destination and returns a 12-month climatology, typical conditions, marine-life season windows, and a source page.species_seasonality accepts a species and optional coordinates, returning a peak month, regional season windows, and sighting counts.site_facts accepts a named site and returns facts such as depth, difficulty, access type, hazards, entry and exit notes, and certification level.top_dive_regions ranks world regions by favorable windows over approximately the next 72 hours.The tools do not create, modify, or delete data. They expose public dive information through read operations only.
Forecast grades are planning context rather than safety clearance for a specific dive. Conditions should still be assessed locally, and users should follow their training and local guidance. Species seasonality reflects recorded sightings and does not guarantee an encounter.
Coverage and historical depth can vary by destination. A response may state that there is not enough history when the dataset cannot support a reliable seasonal answer. The service also applies rate limiting, so bulk or sustained automated use may require prior contact with PickADive.
Factual signals from GitHub, npm, and our automated checks β not a rating.
No reviews yet β be the first to share how this listing worked for you.
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/pickadive-scuba-diving)<a href="https://allmcps.com/mcp/pickadive-scuba-diving"><img src="https://allmcps.com/api/badge/pickadive-scuba-diving?style=directory" alt="PickADive Scuba Diving on AllMCPs" /></a>