MCP MCP Server

<b>Query 700,000+ ocean & atmospheric datasets from inside Claude, ChatGPT, Gemini, Cursor, and any MCP client — no API keys, no schemas, no glue

Remote serverstreamable-httpPython

What is the MCP MCP server?

MCP MCP server is a hosted integration for AI assistants that speak the Model Context Protocol. Query 700,000+ ocean & atmospheric datasets from inside Claude, ChatGPT, Gemini, Cursor, and any MCP client — no API keys, no schemas, no glue code..

What you get

AQUAVIEW MCP is a hosted Model Context Protocol server that gives any LLM agent direct, structured access to a unified catalog of 700,000+ oceanographic, atmospheric, and marine datasets drawn from 68 authoritative sources — NOAA, all 11 IOOS Regional Associations, the World Ocean Database, the Global Argo array, GOES-R satellites, NEXRAD weather radar, ESA Sentinel, IFREMER, EMODnet, Ocean Networks Canada, and more.

Setting it up

Being a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.

What the assistant can call

Once MCP is connected, these are the calls the assistant has available:

  • list_collections — Enumerate all 68 sources with bbox, temporal extent, keywords
  • search_datasets — Free-text + spatial + temporal + CQL2 search across the unified STAC catalog
  • aggregate — Counts, geohash heatmaps, per-collection breakdowns, datetime histograms
  • get_item — Fetch a single STAC item with full properties and asset download URLs
  • Cursor — Settings → MCP → Add new MCP Server, paste the URL above, type http

Before you rely on it

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the mcp mcp server does with a few real requests.

Choosing this one

This sits in the developer tooling group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. MCP's toolset — list_collections, search_datasets, aggregate and 2 more — is a fair guide to whether it matches your workflow. It is maintained by aquaview-dah; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against MCP's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Available tools

ToolWhat it does
list_collectionsEnumerate all 68 sources with bbox, temporal extent, keywords
search_datasetsFree-text + spatial + temporal + CQL2 search across the unified STAC catalog
aggregateCounts, geohash heatmaps, per-collection breakdowns, datetime histograms
get_itemFetch a single STAC item with full properties and asset download URLs
CursorSettings → MCP → Add new MCP Server, paste the URL above, type http.

Example prompts to try

  • Use MCP to list collections.
  • Use MCP to search datasets.
  • Use MCP to aggregate.

Frequently asked questions

It connects MCP to MCP-compatible AI assistants such as Claude and Cursor, exposing 5 tools (list_collections, search_datasets, aggregate, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with MCP directly.