Skip to main content

OFS MCP Server

MCP server for NOAA's Operational Forecast System (OFS) — regional hydrodynamic ocean models covering US coastal waters.

Status: Ready

Overview

OFS comprises ~15 regional ocean models providing 48–72 hour forecasts of water levels, temperature, and salinity for US coastal bays, estuaries, and offshore waters. This server provides AI assistants with access to model metadata, cycle availability, and forecast extraction at geographic points.

Supported Models

Model Name Grid Region
cbofs Chesapeake Bay OFS ROMS Chesapeake Bay, MD/VA
dbofs Delaware Bay OFS ROMS Delaware Bay, DE/NJ
gomofs Gulf of Maine OFS ROMS Gulf of Maine, ME/MA
ngofs2 N. Gulf of Mexico OFS v2 FVCOM Gulf Coast, LA/TX
nyofs New York/NJ Harbor OFS POM NY Harbor, NY/NJ
sfbofs San Francisco Bay OFS FVCOM San Francisco Bay, CA
tbofs Tampa Bay OFS ROMS Tampa Bay, FL
wcofs West Coast OFS ROMS US West Coast, CA–WA
ciofs Cook Inlet OFS ROMS Cook Inlet, AK

All models run 4× daily (2× for WCOFS) at 00, 06, 12, 18 UTC with 6-minute output resolution.

Tools

Tool Description
ofs_list_models List all supported models with metadata
ofs_get_model_info Detailed specs for a specific model
ofs_list_cycles Check S3 for available forecast cycles
ofs_find_models_for_location Which models cover a lat/lon point
ofs_get_forecast_at_point Forecast time series at lat/lon
ofs_compare_with_coops Compare model vs CO-OPS observations

Data Access

Model data is accessed via two strategies:

  • NOAA THREDDS OPeNDAP (https://opendap.co-ops.nos.noaa.gov/thredds/): lazy remote access to BEST aggregations (most efficient, only loads requested variables/points)
  • AWS S3 (noaa-nos-ofs-pds): direct download for single forecast timesteps

Quick Start

cd servers/ofs-mcp
uv sync
uv run ofs-mcp

MCP Client Config

{
  "mcpServers": {
    "ofs": {
      "command": "uv",
      "args": ["--directory", "/path/to/ocean-mcp/servers/ofs-mcp", "run", "ofs-mcp"]
    }
  }
}

Example Queries

  • "What OFS models cover the Chesapeake Bay?"
  • "List available CBOFS forecast cycles for today"
  • "Get the water level forecast at lat 38.98, lon -76.48 from CBOFS"
  • "Compare CBOFS water level with CO-OPS observations at station 8571892"
  • "What OFS models are available for San Francisco Bay?"
  • "Get temperature forecast at lat 37.8, lon -122.4 from SFBOFS"

Variables

All models provide surface-layer output:

Variable Units Description
water_level m Surface elevation relative to model datum
temperature °C Water temperature at surface sigma layer
salinity PSU Salinity at surface sigma layer

Datum Notes

Most OFS models use NAVD88 as their vertical datum. CO-OPS observations use either NAVD or MSL depending on the station. Small systematic offsets (1–5 cm) are expected when comparing model output to observations due to datum differences and distance between CO-OPS stations and model grid points.

Data Sources

License

MIT

Metadata

Release files for ofs-mcp 0.1.2

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for ofs-mcp 0.1.2
File Size Uploaded
ofs_mcp-0.1.2.tar.gz 42.6 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for ofs-mcp 0.1.2
File Interpreter ABI Platform
ofs_mcp-0.1.2-py3-none-any.whl Python 3 none any Details

Total release size: 72.2 kB

Release files / ofs_mcp-0.1.2.tar.gz

Download URL ofs_mcp-0.1.2.tar.gz
Size 42.6 kB
Tags Source
SHA-256 checksum
How to use checksums
509759cd4b015112e77d313c57d8b50d05c289c56da6b6a55ab38a5a742f62a6
BLAKE2b-256 checksum
How to use checksums
02ea5feb12b5e9dc04542c554833f84333f73b0c652173971773b06285d73ba7
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 4, 2026.

Transparency log

Release files / ofs_mcp-0.1.2-py3-none-any.whl

Download URL ofs_mcp-0.1.2-py3-none-any.whl
Size 29.6 kB
Tags Python 3
SHA-256 checksum
How to use checksums
cde721fd56d706fd60a3fe21d2b8fce9dfb4300a9242397f0d7f2a5db396544d
BLAKE2b-256 checksum
How to use checksums
37d35a0bfd4ab6209130c592a7fb5ad9074b8a70a897b2aee5eed383f61770a6
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 4, 2026.

Transparency log

Release history Release notifications | RSS feed

This release

0.1.2 This release

2 release files

0.1.1

2 release files

0.1.0

2 release 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