gribstream_list_datasetsLABSCO SUMMARY
You can find the variable before you have an account.
The discovery and request-building tools are public and read-only, so the hard part — working out which dataset and which exact selector answer your question — happens before authentication. Every tool description starts with either NO AUTH / PUBLIC / READ-ONLY or AUTH REQUIRED / DATA QUERY, which is how a client keeps metadata work and billed data work apart.
What it is
A hosted MCP server for weather forecast data from GribStream, covering NOAA GFS, HRRR and NBM and ECMWF IFS among others. Discovery, selector lookup, request building and validation work before you authenticate; running an actual query needs OAuth.
What you get
- Dataset discovery —
gribstream_list_datasets,gribstream_get_dataset - Finding the exact variable —
gribstream_list_parameters,gribstream_get_parameter,gribstream_list_shared_parameters,gribstream_resolve_shared_parameter,gribstream_get_expression_reference - Request building —
gribstream_build_timeseries_requestfor values by valid time,gribstream_build_runs_requestto compare forecasts across model runs, both returning a copy-pasteable authenticated request without sending it - gribstream_validate_request — check request shape, selector tuples and expression syntax without querying values
- Live queries after OAuth —
gribstream_query_timeseriesandgribstream_query_runsreturn actual weather values - Prompts for common jobs:
choose_weather_dataset,find_weather_variable,compare_forecast_runs,create_grid_requestand more - Resources:
gribstream://openapiandgribstream://skill/gribstream-query
Requirements
A client that speaks remote Streamable HTTP, pointed at https://gribstream.com/mcp with no trailing punctuation. Live queries need OAuth, which most clients discover automatically; if yours asks for manual fields, the client ID is gribstream-mcp-public and the client secret must be left empty — a form that demands one is asking for a confidential-client flow this does not support. The OAuth flow asks you to pick an active GribStream API token, and the client never sees that raw token. Results come back as CSV, JSON, NDJSON or Parquet; max_bytes caps inline results at 10,000,000 bytes, and dense grids should use delivery=url instead.
Setup effort
Paste a URL — add the endpoint to your client
USE CASES
01
Picking a forecast model for your region and horizon
List the datasets and read the tradeoffs before committing to one.
02
Finding the exact selector for a weather signal
Resolve the shared parameter or read the dataset's own parameter metadata.
03
Getting a runnable request you can check first
Build the timeseries request, validate its selectors and expression syntax, and keep the curl.
04
Comparing how a forecast changed between runs
Build and run a /runs request across model runs and lead times.
12 tools
Listed in project docs. Your client may show a different list.
gribstream_get_datasetgribstream_list_parametersgribstream_get_parametergribstream_list_shared_parametersgribstream_resolve_shared_parametergribstream_get_expression_referencegribstream_build_timeseries_requestgribstream_build_runs_requestgribstream_validate_requestgribstream_query_timeseriesgribstream_query_runsBEFORE YOU INSTALL
What to know first
Tools you get
12 tools named in the project's documentation.
Requires
A client that can reach a remote MCP server over HTTP
Where it runs
All 3 documented setups connect to a hosted endpoint.
INSTALLATION
Connect your client
Add the endpoint to your client.
Server setup
ENDPOINT URL
https://gribstream.com/mcpMCP Clients
Any MCP client — remote HTTP
ANY MCP CLIENT — REMOTE HTTP · JSON
{
"mcpServers": {
"gribstream": {
"url": "https://gribstream.com/mcp"
}
}
}LobeHub
LOBEHUB · JSON
{
"mcpServers": {
"gribstream": {
"type": "http",
"url": "https://gribstream.com/mcp"
}
}
}Any MCP client — explicit transport
ANY MCP CLIENT — EXPLICIT TRANSPORT · JSON
{
"mcpServers": {
"gribstream": {
"type": "streamable-http",
"url": "https://gribstream.com/mcp"
}
}
}Clients spell the "type" value differently: Claude Code and VS Code use "http", Cline uses "streamableHttp", and Roo Code uses "streamable-http". Claude Desktop does not accept a URL entry in its config file; remote servers go under Settings → Connectors.
