Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

NOAA WW3 MCP Server

PYPI · WW3-MCP

GFS-Wave (WAVEWATCH III) forecasts and NDBC buoy wave observations

Available components

−15 this week 75 Trust /100

Last scanned (10 hours ago)

Scores higher than 68% of PyPI servers

Category Maps and Location

Recent critical change

GHSA-6q48-6c7w-9gw2 affects this package (21 Oct 2026). See the changelog before you install this server.

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security50
  • Malware scan not yet available for this package.Unverified
  • No known CVEs affecting this package version or its production dependencies.Pass
  • Runs hatchling.build at install time, a recognised build step with no custom scripting around it. View diagnostics → Pass
  • 0 of 39 dependencies flagged as unhealthy. View diagnostics → Pass
Provenance & Transparency100
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Cryptographically verified build provenance (signed, bound to oceanmodeling/ocean-mcp). View diagnostics → Pass
  • Clear OSI-approved license (MIT).Pass
  • Actively maintained (last published 5 days ago).Pass
  • Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability59
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 1774 tokens (~197/item across 9 items; 9 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage71
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 0% of tool parameters carry a description.Fail
  • Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 9 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 9 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
What we tested

Checks we ran (15)

  • Known CVEs
  • Install scripts
  • Dependency health
  • Source repository
  • Provenance
  • License
  • Maintenance
  • Security disclosure
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Checks we could not complete (1)

These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • Malware scan in Supply Chain SecurityMalware scan not yet available for this package.

Does not apply to this package (2)

  • Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
  • Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 21 Nov 26 −15
    • Malware scan: pass → unverified ▼ security
  • 19 Nov 26 +15
    • Malware scan: unverified → pass ▲ security
    • Stability: 0.97 → pass security
  • 18 Nov 26 −15
    • Malware scan: pass → unverified ▼ security
    • Stability: pass → 0.97 functional
  • 17 Nov 26 +15
    • Malware scan: unverified → pass ▲ security
  • 16 Nov 26 −15
    • Malware scan: pass → unverified ▼ security
    • Schema quality: 164 → 197 ▼ functional
    • Package version: 0.1.2 → 0.1.3 functional
  • 13 Nov 26 +15
    • Malware scan: unverified → pass ▲ security
  • 12 Nov 26 0
    • Stability: 0.97 → pass security
  • 11 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Analysed pypi/ww3-mcp@0.1.3

Provenance Verified

A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.

Result Verified
Ecosystem pypi
Reason Verified
Discovered via Registry attestation endpoint
Source repo oceanmodeling/ocean-mcp
Certificate issuer https://token.actions.githubusercontent.com
Certificate SAN https://github.com/oceanmodeling/ocean-mcp/.github/workflows/publish.yml@refs/tags/ww3-mcp-v0.1.3
Rekor log index 3913864019
Predicate type PyPI publish attestation https://docs.pypi.org/attestations/publish/v1
Subject digest sha256:55fd6ddd6ce5cf1dceed483f89fce4af2f2d7f24485d49b54510c99f3f0e5937

Background: How many MCP packages publish verified provenance →

Install scripts 1 script
Hook Tier Command
build_backend Known build tool hatchling.build

Background: Why install scripts are a supply-chain risk →

Dependencies 39 packages
Packages resolved 39
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 9 exposed · ~1,774 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
ww3_compare_forecast_with_buoy ~255

Compare GFS-Wave forecast with NDBC buoy observations. Fetches both the model forecast and buoy observations for wave height, aligns the time series, and computes validation statistics (bias, RMSE, MAE, peak error, correlation). Args: station_id: NDBC buoy station ID (e.g., '41025', '46042'). buoy_lat: Buoy latitude in decimal degrees. buoy_lon: Buoy longitude in decimal degrees. grid: Wave grid to use (default: 'global.0p25'). hours_to_compare: Hours of comparison (default 24, max 120). Sets both the forecast hours fetched (0 to hours_to_compare, every 3 h) and the observation window: the buoy rows within this many hours before its latest row, selected by timestamp at whatever interval the station reports. response_format: 'markdown' (default) or 'json'.

NameTypeReqDescription
buoy_latnumberyes–
buoy_lonnumberyes–
grid–––
hours_to_compareinteger––
response_formatstring––
station_idstringyes–
NameTypeReqDescription
resultstringyes–

No examples provided.

ww3_find_buoys ~155

Find NDBC buoys near a geographic location. Searches the NDBC active stations registry for buoys within a specified radius of a lat/lon point. Returns station IDs, distances, and metadata. Args: latitude: Target latitude in decimal degrees. longitude: Target longitude in decimal degrees. radius_km: Search radius in kilometers (default 200). limit: Maximum number of buoys to return (default 10). response_format: 'markdown' (default) or 'json'.

NameTypeReqDescription
latitudenumberyes–
limitinteger––
longitudenumberyes–
radius_kmnumber––
response_formatstring––
NameTypeReqDescription
resultstringyes–

No examples provided.

ww3_get_buoy_history ~266

Get historical annual wave observations from an NDBC buoy. Fetches NDBC's historical annual standard meteorological file for one year. Missing values, which these files mark with 9-filled codes (e.g. WVHT 99.00), are returned as null and counted, never as measurements. The wave-height summary (valid count, min, max and its time, mean) covers every row of the file. The rows returned are the most recent max_records rows of the year (the file is oldest-first), and the response states how many rows the file has and how many were returned. Args: station_id: NDBC station ID (e.g., '41025', '46042'). year: Year to fetch (e.g., 2023). NDBC publishes an annual file only after the year has ended. max_records: Maximum rows to return (default 500, max 5000). Does not change the summary, which always covers the whole file. response_format: 'markdown' (default) or 'json'.

NameTypeReqDescription
max_recordsinteger––
response_formatstring––
station_idstringyes–
yearintegeryes–
NameTypeReqDescription
resultstringyes–

No examples provided.

ww3_get_buoy_observations ~271

Get recent wave observations from an NDBC buoy. Fetches realtime standard meteorological data from NDBC including wave height, dominant period, average period, mean wave direction, wind speed, and wind direction. NDBC's realtime file holds about the last 45 days, at the station's own reporting interval (e.g. 10 minutes at 41009, 30 at 44025; NDBC says most stations report hourly). The window is selected by timestamp, so it covers the requested hours at any interval. Args: station_id: NDBC station ID (e.g., '41025', '46042', '44013'). hours: Hours of observations to return, counted back from the latest row in the file (default 24, max 1080). response_format: 'markdown' (default) or 'json'. max_records: Cap on JSON rows returned (default 2000). Rows are newest-first, so the most recent are kept, and the response flags any truncation. The markdown summary covers the whole window.

NameTypeReqDescription
hoursinteger––
max_recordsinteger––
response_formatstring––
station_idstringyes–
NameTypeReqDescription
resultstringyes–

No examples provided.

ww3_get_forecast_at_point ~250

Get GFS-Wave forecast time series at a geographic point. Downloads subsetted GRIB2 data from NOMADS for multiple forecast hours and extracts wave variables at the nearest grid point. This is the primary tool for wave forecast data. Args: latitude: Target latitude in decimal degrees (-90 to 90). longitude: Target longitude in decimal degrees (-180 to 180). grid: Wave grid to use (default: 'global.0p25'). variables: List of wave variables to retrieve (e.g., ['HTSGW', 'PERPW', 'DIRPW']). Default: ['HTSGW', 'PERPW', 'DIRPW']. max_hours: Maximum forecast hours to retrieve (default 120, max 384). step_hours: Hours between forecast steps (default 3, min 1). response_format: 'markdown' (default) or 'json'.

NameTypeReqDescription
grid–––
latitudenumberyes–
longitudenumberyes–
max_hoursinteger––
response_formatstring––
step_hoursinteger––
variables–––
NameTypeReqDescription
resultstringyes–

No examples provided.

ww3_get_point_snapshot ~171

Get all wave variables at a single point and forecast time. Downloads a single GRIB2 file and extracts all available wave variables at the nearest grid point. Use this for a quick snapshot of current or near-future conditions. Args: latitude: Target latitude in decimal degrees. longitude: Target longitude in decimal degrees. forecast_hour: Forecast hour (0=analysis, 6, 12, ..., max 384). Default: 0. grid: Wave grid to use (default: 'global.0p25'). response_format: 'markdown' (default) or 'json'.

NameTypeReqDescription
forecast_hourinteger––
grid–––
latitudenumberyes–
longitudenumberyes–
response_formatstring––
NameTypeReqDescription
resultstringyes–

No examples provided.

ww3_get_regional_summary ~192

Get spatial statistics for wave variables over a bounding box. Downloads a single GRIB2 file subsetted to the bounding box and computes min, max, mean, and standard deviation for each wave variable. Args: lat_min: Southern latitude bound. lat_max: Northern latitude bound. lon_min: Western longitude bound (-180 to 180). lon_max: Eastern longitude bound (-180 to 180). forecast_hour: Forecast hour (default 0). grid: Wave grid to use (default: 'global.0p25'). response_format: 'markdown' (default) or 'json'.

NameTypeReqDescription
forecast_hourinteger––
grid–––
lat_maxnumberyes–
lat_minnumberyes–
lon_maxnumberyes–
lon_minnumberyes–
response_formatstring––
NameTypeReqDescription
resultstringyes–

No examples provided.

ww3_list_cycles ~126

Check available GFS-Wave forecast cycles on NOAA servers. Checks AWS S3 for available GRIB2 files to determine which forecast cycles have been published. Useful before calling ww3_get_forecast_at_point. Args: grid: Wave grid to check (default: 'global.0p25'). date: Specific date in YYYY-MM-DD format. Default: today UTC. num_days: Number of past days to check (1-7). Default: 2.

NameTypeReqDescription
date–––
grid–––
num_daysinteger––
NameTypeReqDescription
resultstringyes–

No examples provided.

ww3_list_grids ~88

List available GFS-Wave (WAVEWATCH III) model grids with resolution and domain info. Returns grid IDs, resolution, geographic coverage, forecast length, and available wave variables. Use this to choose a grid for ww3_get_forecast_at_point. Args: response_format: 'markdown' (default) or 'json'.

NameTypeReqDescription
response_formatstring––
NameTypeReqDescription
resultstringyes–

No examples provided.

Install

How do I install the NOAA WW3 MCP Server server?

NOAA WW3 MCP Server runs locally as a PyPI package, launched with uvx ww3-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

pypi · ww3-mcp

# add to Claude Code
claude mcp add oceanmodeling-ww3-mcp -- uvx ww3-mcp
Common questions

What is the NOAA WW3 MCP Server server?

NOAA WW3 MCP Server is listed in the public MCP registry as io.github.oceanmodeling/ww3-mcp. GFS-Wave (WAVEWATCH III) forecasts and NDBC buoy wave observations. This page covers its PyPI package (ww3-mcp).

Is the NOAA WW3 MCP Server server safe to use?

NOAA WW3 MCP Server scores 75 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the NOAA WW3 MCP Server server expose?

NOAA WW3 MCP Server exposes 9 tools: ww3_get_buoy_observations, ww3_get_buoy_history, ww3_list_grids, ww3_list_cycles, ww3_find_buoys, and 4 more. Their descriptions and schemas cost roughly 1,774 tokens of context every time the server is loaded.

Is the NOAA WW3 MCP Server server still maintained?

NOAA WW3 MCP Server is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the NOAA WW3 MCP Server server under?

NOAA WW3 MCP Server declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

What did VerifyMCP test on the NOAA WW3 MCP Server server?

VerifyMCP ran 15 checks on NOAA WW3 MCP Server, covering Known CVEs, Install scripts, Dependency health, Source repository and 11 more. One item could not be completed, a gap on our side rather than a finding about NOAA WW3 MCP Server: Malware scan. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.