An MCP server for NOAA's Operational Forecast System that exposes regional ocean model metadata, forecast cycle availability, location coverage, and point forecast extraction. It also supports comparing OFS model output with CO-OPS observations.
From the registry: NOAA OFS regional ocean model forecasts — water level, temperature, salinity
Please install the `ofs-mcp` MCP server into my current AI client (that's you).
Optional prerequisites:
- Install uv — Install the uv Python package manager/runtime to sync dependencies and run the MCP server. (https://docs.astral.sh/uv/'}? Wait cannot invent malformed link.)
Canonical MCP server config (stdio transport):
- command: `uv`
- args: ["--directory","<path-to-ocean-mcp/servers/ofs-mcp>","run","ofs-mcp"]
Note: README provides a local stdio launch method using uv from the server directory. No environment variables or API keys are documented. The shown client JSON was wrapper config; extracted here is only the inner command/args shape.
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.