RTOFS MCP Server

MCP server for accessing NOAA RTOFS (Real-Time Ocean Forecast System) global ocean forecast data. Provides SST, salinity, ocean currents, and sea surface height from the operational HYCOM/ESPC model via the HYCOM THREDDS Data Server.

Features

  • Global 1/12° ocean forecasts (~8 km resolution)
  • 8-day forecast horizon, updated daily
  • Temperature, salinity, currents at all depth levels
  • Sea surface height (SSH) at hourly resolution
  • Point queries, depth profiles, area grids, and vertical transects
  • Pure httpx — no NetCDF/xarray dependencies needed

Installation

# Using uvx (recommended)
uvx rtofs-mcp

# Using pip
pip install rtofs-mcp

Tools

Tool Description
rtofs_get_system_info RTOFS overview — resolution, variables, coverage (no HTTP)
rtofs_list_datasets List HYCOM THREDDS datasets with live availability check
rtofs_get_latest_time Query latest forecast time from THREDDS
rtofs_get_surface_forecast Surface time series at a point (SST, SSS, currents, SSH)
rtofs_get_profile_forecast 3D depth profile at a point (temp, salinity, currents vs depth)
rtofs_get_area_forecast Surface forecast for a bounding box (parallel point queries)
rtofs_get_transect Vertical transect between two points (parallel depth profiles)
rtofs_compare_with_observations Compare forecast values at different times

Example Queries

  • "What is the current SST at The Battery, NYC?"
  • "Show me a temperature depth profile at 35°N, 74°W in the Gulf Stream"
  • "Get the SST forecast for the next 8 days at latitude 25, longitude -80"
  • "Show a vertical transect of temperature from Miami to Bermuda"
  • "What are the ocean currents at 40°N, 74°W?"

Data Source

HYCOM THREDDS Data Server (https://tds.hycom.org/thredds/)

ESPC-D-V02 datasets (operational HYCOM/RTOFS):

  • FMRC_ESPC-D-V02_ssh — Sea Surface Height (2D, hourly)
  • FMRC_ESPC-D-V02_t3z — Water Temperature (3D, daily)
  • FMRC_ESPC-D-V02_s3z — Salinity (3D, daily)
  • FMRC_ESPC-D-V02_uv3z — Ocean Currents u/v (3D, daily)

Data is queried via THREDDS NCSS (NetCDF Subset Service) which returns CSV for point queries — no NetCDF library required.

Configuration

Claude Desktop

{
  "mcpServers": {
    "rtofs": {
      "command": "uvx",
      "args": ["rtofs-mcp"]
    }
  }
}

Development

cd servers/rtofs-mcp
uv sync --group dev
uv run rtofs-mcp                                          # Start server
uv run pytest tests/ --ignore=tests/test_live.py -v       # Unit tests
uv run pytest tests/test_live.py -v                       # Integration tests

License

MIT

Project links

Data verified by PyPI on Jul 28, 2026
Data provided by the project maintainers, verified at the time the release was uploaded to PyPI.

Key dates

PyPI data
Data sourced directly from PyPI's database.
  • Released:
Latest release

1 maintainer

PyPI data
Data sourced directly from PyPI's database.
Avatar for mjisan from gravatar.com mjisan

Credits

Author: Mansur Ali Jisan

GitHub Statistics

Data verified by PyPI on Jul 28, 2026
The GitHub source repository was provided by the project maintainers and verified by PyPI at the time of upload. Stars, forks, and open issues/PRs are derived from that repository and have not been independently verified.

License expression

MIT
View SPDX License List

Requires

Python >=3.11

Tags

hycom mcp model-context-protocol noaa ocean-currents ocean-forecast oceanography rtofs sst

Classifiers

Report project as malware

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

rtofs_mcp-0.1.2.tar.gz (23.0 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

rtofs_mcp-0.1.2-py3-none-any.whl (19.8 kB view details)

Uploaded Python 3

File details

Details for the file rtofs_mcp-0.1.2.tar.gz.

File metadata

  • Download URL: rtofs_mcp-0.1.2.tar.gz
  • Upload date:
  • Size: 23.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.14

File hashes

Hashes for rtofs_mcp-0.1.2.tar.gz
Algorithm Hash digest
SHA256 5303e7530f5a84cc094deeae3dc81239d9eb7b8a1336134adfd4eb75e74a7898
MD5 d9974ec98461722d6fe5122677c3ef9c
BLAKE2b-256 40e119ee9485c88b2188ab3bf7bcc5751d98ce4a1069cdc3ba27012acd8935ea

See more details on using hashes here.

Provenance

The following attestation bundles were made for rtofs_mcp-0.1.2.tar.gz:

Publisher: publish.yml on mansurjisan/ocean-mcp

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file rtofs_mcp-0.1.2-py3-none-any.whl.

File metadata

  • Download URL: rtofs_mcp-0.1.2-py3-none-any.whl
  • Upload date:
  • Size: 19.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.14

File hashes

Hashes for rtofs_mcp-0.1.2-py3-none-any.whl
Algorithm Hash digest
SHA256 72a793ee7aebdb1be882eea4188f3f72601d8c24171101526b97335e68821e2d
MD5 8cca049d483e7083ff4b667c78831a6a
BLAKE2b-256 31f57787ba40dd59a007814e5c500666d9ebf4199886d935201d00430535f9e4

See more details on using hashes here.

Provenance

The following attestation bundles were made for rtofs_mcp-0.1.2-py3-none-any.whl:

Publisher: publish.yml on mansurjisan/ocean-mcp

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Release history Release notifications | RSS feed

This release

0.1.2 This release

2 files

0.1.1

2 files

0.1.0

2 files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page