Noaa Ndbc MCP server

@pipeworx/noaa-ndbc

Observed marine conditions from NOAA's National Data Buoy Center — ~1,350 active moored buoys, coastal C-MAN stations, DART tsunami stations and partner platforms reporting wave height, wave period, sea-surface temperature, wind and pressure.

Part of Pipeworx — an MCP gateway connecting AI agents to 1679+ live data sources.

Tools

• ndbcstations(bbox?, nearlatitude?, nearlongitude?, namecontains?, owner?, type?, hasmet?, haswaterquality?, has_currents?, limit?) — the active-station inventory, distance-ranked when a point is given.
• ndbclatestobs(station_id) — the newest standard meteorological observation at one station.
• ndbcstationhistory(station_id, hours?, limit?) — up to ~45 days of rows, newest first.

Auth

Keyless. NDBC serves nothing without a User-Agent, which this pack always sends.

Data sources

• https://www.ndbc.noaa.gov/activestations.xml — active-station inventory.
• https://www.ndbc.noaa.gov/data/realtime2/.txt — last ~45 days of observations.

Things the next person would otherwise rediscover:

numeric here is null when the station did not report it; a buoy reporting wind but no wave height is normal.

• Missing values are the literal string MM, not an empty field. Every

are parsed positionally because some partner stations abbreviate the header.

• realtime2 rows are NEWEST FIRST. Row 0 is the latest.
• Two # header lines, the first names columns and the second units. Columns

platforms 404 there. That is a coverage fact about the station, and ndbclatestobs says so rather than reporting an outage.

• Not every active station has a realtime2 file. DART and water-quality-only

Quick Start

Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):

{
  "mcpServers": {
    "noaa-ndbc": {
      "url": "https://gateway.pipeworx.io/noaa-ndbc/mcp"
    }
  }
}

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/noaa-ndbc/mcp returns the tools in the table above plus the shared Pipeworx meta-tools — askpipeworx, discovertools, search_within, remember/recall and the rest of the gateway-wide set. So the tool count you see is larger than this table: a single-pack endpoint currently lists roughly 30 shared tools alongside the pack's own. The connection's initialize response states its exact scope, and is the authoritative answer for a given day.

This is deliberate, not multiplexing by accident. The meta-tools are what let a scoped connection answer a question this pack does not cover — via ask_pipeworx, which routes across the whole catalog — without you adding a second MCP server. There is currently no way to mount a pack endpoint without them; if the extra schemas cost you more context than the routing is worth, connect to the full gateway once rather than to several pack endpoints.

Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:

{
  "mcpServers": {
    "pipeworx": {
      "url": "https://gateway.pipeworx.io/mcp"
    }
  }
}

Both URLs reach the same gateway and the same 1679+ data sources. The only difference is which pack's tools are listed directly; ask_pipeworx reaches all of them from either one.

No MCP client? Call it over HTTP

curl -X POST https://gateway.pipeworx.io/v1/tools/ndbc_stations \
  -H 'Content-Type: application/json' \
  -d '{"near_latitude":37.77,"near_longitude":-122.42,"has_met":true,"limit":5}'

No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/ndbcstations. Find one: POST https://gateway.pipeworx.io/v1/tools/searchpacks with {"query":"..."}.

Standalone (no gateway account)

This package also runs as a local stdio MCP server — no Pipeworx account, no gateway round-trip:

Shortened. The full README is on GitHub.