NHC MCP Server
MCP server providing AI assistants with access to National Hurricane Center (NHC) storm tracks, advisories, and best track data.
Status: Ready
Tools
| Tool | Description | Status |
|---|---|---|
nhc_get_active_storms |
Get currently active tropical cyclones | Ready |
nhc_get_forecast_track |
Get official NHC 5-day forecast track positions | Ready |
nhc_get_best_track |
Get best track data for historical or recent storms | Ready |
nhc_search_storms |
Search historical storms by name, year, basin, intensity | Ready |
nhc_get_storm_watches_warnings |
Get active watches and warnings for a storm | Ready |
nhc_generate_parametric_wind |
Generate parametric wind field for a storm | Planned |
Data Sources
- CurrentStorms.json — Real-time active storm information from NHC
- ATCF B-deck — Current-season best track data (Automated Tropical Cyclone Forecasting)
- HURDAT2 — Atlantic (1851–2024) and East Pacific (1949–2024) hurricane database
- NHC ArcGIS MapServer — Forecast tracks, cones, and watch/warning polygons
Quick Start
git clone https://github.com/oceanmodeling/ocean-mcp.git
cd ocean-mcp/servers/nhc-mcp
uv sync
Configure your MCP client
{
"mcpServers": {
"nhc": {
"command": "uv",
"args": ["run", "--directory", "/path/to/ocean-mcp/servers/nhc-mcp", "python", "-m", "nhc_mcp"]
}
}
}
Example Queries
- "Are there any active tropical cyclones right now?"
- "Show me Hurricane Katrina's track"
- "Search for Category 5 hurricanes in the Atlantic since 2000"
- "What is the forecast track for the active storm AL052024?"
- "Find all storms named Maria"
Running Tests
# Unit tests (fast, no network)
uv run pytest tests/test_utils.py tests/test_client.py -v
# Live integration tests (requires internet)
uv run pytest tests/test_live.py -v -s
License
MIT
Metadata
Release files for nhc-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 | |
|---|---|---|---|
| nhc_mcp-0.1.1.tar.gz | 33.0 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| nhc_mcp-0.1.1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 53.8 kB
Release files / nhc_mcp-0.1.1.tar.gz
| Download URL | nhc_mcp-0.1.1.tar.gz |
|---|---|
| Size | 33.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
674475a7a8a13fea727576ae86a8eb912ed3c03875575f174c7a33b1e333686e
|
|
BLAKE2b-256 checksum How to use checksums |
063e67394d98aa7444c927708e9969ce5f29982e65a42b49be8a195762bd42e4
|
| 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 1, 2026.
Transparency logRelease files / nhc_mcp-0.1.1-py3-none-any.whl
| Download URL | nhc_mcp-0.1.1-py3-none-any.whl |
|---|---|
| Size | 20.8 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
34bd7bb5b2b1dc6995d20572acff5afc47b198d69570b93bfd5e037035811c25
|
|
BLAKE2b-256 checksum How to use checksums |
8298467653e6514a023ce7f3a7c46a33ba071e0bf3ce7cde4321ef6104ee247b
|
| 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 1, 2026.
Transparency log