Gribstream MCP

Name: Gribstream MCP
Author: GribStream

@GribStream

关于 Gribstream MCP

Historical and real-time weather forecasts of state of the art weather models from NOAA, ECMWF, Google and more. Query and filter data like a database. Full forecast history. Blazing fast. Ideal for bulk data pulls.

#weather #forecast #noaa #ecmwf #historical #timeseries

基本信息

分类

其他

传输方式

stdio

发布者

GribStream

提交者

Alejandro Martínez

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "gribstream": {
      "type": "streamable-http",
      "url": "https://gribstream.com/mcp"
    }
  }
}

工具

List public GribStream datasets. Supports catalog filters such as code, family, tag, and is_ensemble.

Get full public metadata for one dataset code, including archive coverage, cadence, tags, source links, and members.

List parameter summaries for one dataset. Use this before selecting exact case-sensitive parameter codes.

Get detailed metadata and exact selector variations for one dataset parameter. Parameter codes are case-sensitive.

List normalized shared parameter presets that can map one logical signal across datasets.

Resolve one shared parameter preset for a dataset, returning native variables and expressions to use in /timeseries or /runs.

Get the GribStream expression language reference, including github.com/expr-lang/expr syntax guidance, alias rules, examples, and the full exported func.* math function list.

Build and validate a copy-pasteable authenticated /api/v2/{dataset}/timeseries HTTP request without sending it. Use this after creating, editing, or converting a GribStream request. The request body must use exact selectors discovered from the catalog or shared-parameter tools.

Build and validate a copy-pasteable authenticated /api/v2/{dataset}/runs HTTP request without sending it. Use this after creating, editing, or converting a GribStream request. The request body must use exact selectors discovered from the catalog or shared-parameter tools.

Validate the basic shape, exact selector tuples, and expression syntax of a proposed GribStream /timeseries or /runs request without sending it. Use this before returning any hand-edited curl or when changing a request from one dataset to another.

概览

What is GribStream MCP?

GribStream MCP is a hosted Model Context Protocol server for weather forecast data. It helps AI agents discover GribStream datasets, resolve exact forecast variables and levels, validate request bodies, and build runnable GribStream Weather API requests for GFS, ECMWF IFS, NBM, HRRR, and other models.

How to use GribStream MCP?

Connect any MCP client that supports remote Streamable HTTP to the hosted endpoint https://gribstream.com/mcp. Configure the client with a JSON object containing the url field; some clients also require an explicit "type": "streamable-http".

Key features of GribStream MCP

Lists public GribStream weather datasets.
Resolves forecast variables, levels, and aliases.
Builds validated /timeseries and /runs requests.
Generates copy-pasteable curl commands.
Includes prompts for GFS, historical, and forecast requests.

Use cases of GribStream MCP

Choose a forecast model for a region, horizon, or weather task.
Find exact variable selectors, levels, and aliases for a weather need.
Build a /timeseries request for values by valid time.
Build a /runs request to compare forecasts across model runs.
Validate a GribStream API request before running it.

FAQ from GribStream MCP

Is the GribStream MCP server read-only?

Yes. It builds and validates requests but does not execute live /timeseries or /runs data queries.

Do I need an API token to use generated requests?

Generated API requests may require a GribStream API token when you run them outside MCP.

Which weather models does GribStream MCP support?

It supports GFS, ECMWF IFS, NBM, HRRR, and other models available in the GribStream dataset catalog.

What is the endpoint URL for the hosted MCP server?

The hosted endpoint is https://gribstream.com/mcp.

Does the server expose resources or prompts?

Yes. It hosts tools like gribstream_list_datasets, gribstream_build_timeseries_request, and prompts such as build_gribstream_api_request and choose_weather_dataset.