CO-OPS MCP Server
MCP server providing AI assistants with access to NOAA CO-OPS water levels, tides, currents, and coastal oceanographic data.
No API key required — all CO-OPS APIs are free and public.
Features
- Station Discovery — List, search, and find nearest CO-OPS stations by type, state, or coordinates
- Water Levels — Real-time and historical observed water levels with multiple datum references
- Tide Predictions — Harmonic tide predictions (6-min, hourly, or high/low)
- Meteorological Data — Wind, air/water temperature, pressure, humidity, visibility, and more
- Currents — Current observations and predictions from PORTS stations
- Derived Products — Extreme water levels, flood statistics, sea level trends, storm events, tidal datums
Quick Start
Install with uv
git clone https://github.com/oceanmodeling/ocean-mcp.git
cd ocean-mcp/servers/coops-mcp
uv sync
Configure your MCP client
Add to your MCP settings:
{
"mcpServers": {
"coops": {
"command": "uv",
"args": ["run", "--directory", "/path/to/ocean-mcp/servers/coops-mcp", "python", "-m", "coops_mcp"]
}
}
}
Or if installed as a package:
{
"mcpServers": {
"coops": {
"command": "uvx",
"args": ["coops-mcp"]
}
}
}
Available Tools
| Tool | Description | Key Parameters |
|---|---|---|
coops_list_stations |
List CO-OPS stations by type/state | station_type, state, limit |
coops_get_station |
Get detailed station metadata | station_id, expand (sensors, datums, etc.) |
coops_find_nearest_stations |
Find stations near coordinates | latitude, longitude, radius_km |
coops_get_water_levels |
Observed water level data | station_id, begin_date, end_date, datum |
coops_get_tide_predictions |
Tide predictions | station_id, begin_date, end_date, interval |
coops_get_meteorological |
Met observations (wind, temp, etc.) | station_id, product, date |
coops_get_currents |
Current observations/predictions | station_id, product, bin_num |
coops_get_extreme_water_levels |
Record water levels | station_id, datum |
coops_get_flood_stats |
Flood day counts & HTF outlook | station_id, year |
coops_get_sea_level_trends |
Sea level trend data | station_id |
coops_get_peak_storm_events |
Peak storm surge events | station_id, year |
coops_get_datums |
Tidal datum values | station_id, units |
Usage Examples
Ask naturally — the right tool will be selected automatically:
- "Get current water levels at The Battery, NY" →
coops_get_water_levels(station_id="8518750", date="latest") - "Find tide stations near Miami Beach" →
coops_find_nearest_stations(latitude=25.77, longitude=-80.13, station_type="waterlevels") - "What were the highest water levels ever recorded at San Francisco?" →
coops_get_extreme_water_levels(station_id="9414290") - "Show me wind data for Key West today" →
coops_get_meteorological(station_id="8724580", product="wind", date="today") - "What are the flood statistics for The Battery?" →
coops_get_flood_stats(station_id="8518750") - "Get tide predictions for Charleston, SC for next week" →
coops_get_tide_predictions(station_id="8665530", begin_date="...", end_date="...")
API Reference
This server wraps three NOAA CO-OPS APIs:
- Data API — Observations and predictions
- Metadata API — Station information
- Derived Product API — Historical/statistical products
Development
# Install dev dependencies
uv sync
# Run unit tests
uv run pytest tests/test_models.py tests/test_utils.py tests/test_client.py -v
# Run live integration tests (makes real API calls)
uv run pytest tests/test_live.py -v -s
# Start the server
uv run python -m coops_mcp
License
MIT
Release files for coops-mcp 0.1.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| coops_mcp-0.1.1.tar.gz | 50.6 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| coops_mcp-0.1.1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 73.7 kB
Release files / coops_mcp-0.1.1.tar.gz
| Download URL | coops_mcp-0.1.1.tar.gz |
|---|---|
| Size | 50.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
dfb6bd5d6687df6b9f0f335bdad8ccb3340dddc4e94bf47ffc780ca568865a9b
|
|
BLAKE2b-256 checksum How to use checksums |
33e4f9ce429f2751ee370834faffb2ebb0ea3c896d28719372730e03d0e8e0d4
|
| 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 Sep 4, 2026.
Transparency logRelease files / coops_mcp-0.1.1-py3-none-any.whl
| Download URL | coops_mcp-0.1.1-py3-none-any.whl |
|---|---|
| Size | 23.1 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
f9630bc8bf7e024aff0ade1ec2e9a696487e3fdccc1e2b9860a6c5e64846f210
|
|
BLAKE2b-256 checksum How to use checksums |
943ee7214785a3134f6c032946a9ad0e420b20742ac9d3d1db4dd7de6dbf5dc6
|
| 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 Sep 4, 2026.
Transparency log