Gribstream MCP

Created By
GribStream6 days ago
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.
Overview

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.

Hosted MCP endpoint:

https://gribstream.com/mcp

Use Cases

Use GribStream MCP when you want an AI tool to:

  • List public GribStream weather datasets.
  • Choose a forecast model for a region, horizon, or weather task.
  • Find exact variable selectors, levels, and aliases.
  • 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.
  • Generate a copy-pasteable curl command for the GribStream Weather API.

The hosted MCP server is read-only. It builds and validates requests, but it does not execute live /timeseries or /runs data queries. Generated API requests may require a GribStream API token when you run them outside MCP.

Connect

Use the hosted endpoint in any MCP client that supports remote Streamable HTTP:

https://gribstream.com/mcp

Generic configuration shape:

{
  "mcpServers": {
    "gribstream": {
      "url": "https://gribstream.com/mcp"
    }
  }
}

Some clients require an explicit transport field:

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

Capabilities

Hosted tools:

  • gribstream_list_datasets
  • gribstream_get_dataset
  • gribstream_list_parameters
  • gribstream_get_parameter
  • gribstream_list_shared_parameters
  • gribstream_resolve_shared_parameter
  • gribstream_get_expression_reference
  • gribstream_build_timeseries_request
  • gribstream_build_runs_request
  • gribstream_validate_request

Hosted prompts:

  • build_gribstream_api_request
  • build_gfs_forecast_request
  • build_historical_forecast_request
  • create_grid_request
  • compare_forecast_runs
  • choose_weather_dataset
  • find_weather_variable

Hosted resources:

  • gribstream://openapi
  • gribstream://skill/gribstream-query
  • Endpoint: https://gribstream.com/mcp
  • Homepage: https://gribstream.com/mcp
  • Icon: https://gribstream.com/gribstream_small.png
  • OpenAPI: https://gribstream.com/docs/openapi.yaml
  • AI setup docs: https://gribstream.com/ai
  • API dashboard: https://gribstream.com/app/dashboard

Try It

After connecting GribStream MCP to an AI tool, ask:

Use GribStream MCP to build a GFS 2m temperature timeseries request for Houston for tomorrow at 12:00 UTC. Validate the request and return a runnable curl command.

Or:

Use GribStream MCP to find the best dataset for short-range precipitation forecasts in the continental United States. Explain the tradeoffs and build a validated example request.

More examples:

For the GribStream API itself, see the OpenAPI specification.

Server Config

{
  "mcpServers": {
    "gribstream": {
      "type": "streamable-http",
      "url": "https://gribstream.com/mcp"
    }
  }
}
Project Info
Created At
6 days ago
Updated At
5 days ago
Author Name
GribStream
Star
-
Language
-
License
-
Category

Recommend Servers

View All
Coinrebate

2 days ago
Emora Health

a day ago
Nordic Data

2 days ago
Gi
@HasanJahidul

21 hours ago
Nordic Data

2 days ago
MDMagic MCP Server
@MDMagic-MCP

Convert Markdown to DOCX, PDF, and HTML using your own Word templates — your letterhead, your branding, your fonts. Plus 15 designer-built templates for when you don't have your own. MDMagic plugs straight into Claude, Cursor, VS Code, and any MCP-compatible AI assistant, giving them direct access to a professional document conversion pipeline - and, more importantly, *your* templates. ✨ Use your own Word templates Upload your existing letterhead, stationery, brand guidelines, contract shells, proposal templates — anything you already use in Microsoft Word. Once uploaded, your AI assistant can convert any Markdown directly into a polished document carrying *your* logo, fonts, colours, footers, page numbers, watermarks, and signature blocks. The output looks like it came from your design team, not from a generic AI export. 🎨 Or pick from 15 designer-built templates Don't have a Word template ready? MDMagic ships with 15 professionally designed templates across four categories: • Business — Executive Platinum, Financial Blue, Premium Bronze, Professional Azure, Business Purple • Creative — Designer Indigo, Artistic Aqua, Sunset Vibes, Sage Serenity, Minimalist Pro, Cheese Burger • Professional — Legal Burgundy, Modern Legal • Technical — Code Documentation, Deep Data Blue 🧰 Ten tools, designed for AI workflows • convert_document — Markdown → DOCX, PDF, HTML, or all three • validate_markdown — pre-flight syntax check before you spend credits • estimate_conversion_cost — know the cost before the conversion runs • recommend_template — describe the document, get the right template • list_all_templates / list_builtin_templates / list_custom_templates — full catalogue with category filters • get_template_details — confirm page sizes, orientations, variants • check_credit_balance — credits remaining, plan status, cost-aware AI behaviour • show_default_settings — honour the user's preferred page size and orientation 💸 Same credits, one balance Whether you convert via the MDMagic web app or your AI assistant, credits work the same way. Free-tier credits renew monthly. Paid plans and one-off top-ups available. The MCP refuses conversions when your balance is low — no surprise bills. 🚀 Five-minute setup Sign up at https://mdmagic.ai/account → grab your API key → paste a JSON snippet into your AI client's MCP config → restart. Done. The hosted endpoint at https://api.mdmagic.ai/mcp is also available for clients that don't run local processes. Built for serious documents. Designed for AI assistants. Trusted with your brand.

7 hours ago