MCP server for NOAA GFS-Wave (WAVEWATCH III) forecasts and NDBC buoy wave observations. It can fetch forecast, observation, and historical wave data, and compare model forecasts against buoy measurements.
From the registry: GFS-Wave (WAVEWATCH III) forecasts and NDBC buoy wave observations
$ pip install uv$ pip install ww3-mcpPlease install the `ww3-mcp` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install uv** — Install the uv Python package manager to run the server with the recommended uvx command. Run: `pip install uv`
Optional prerequisites:
- Alternative: install Python package with pip — You can alternatively install the ww3-mcp package with pip instead of using uvx. Run: `pip install ww3-mcp`
Canonical MCP server config (stdio transport):
- command: `uvx`
- args: ["ww3-mcp"]
Note: No API keys are required. The README also mentions a pip install option, but the canonical MCP config shown uses the recommended uvx launcher.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.