Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Space Weather Data MCP Server What is the current space weather forecast?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
An MCP (Model Context Protocol) server that gives AI assistants access to real-time space weather data and forecasts from NOAA's Space Weather Prediction Center (SWPC).
This server exposes NOAA's SWPC data services to any MCP-compatible AI client. The assistant can browse the data directory, fetch live observations and forecasts, look up product definitions, and interpret values using built-in space weather knowledge — all without leaving the conversation.
Tools (callable by the AI on demand):
Tool | Description |
| Curated map of the SWPC data server layout and notable files |
| Browse any directory on the SWPC data server |
| Fetch a JSON or text data file and return its contents |
| NOAA G/S/R storm scales and solar flare A–X classification |
| Catalog of all SWPC products with descriptions and data file paths |
| Fetch the full description of any SWPC product from the NOAA website |
| Field definitions and interpretation guide for key JSON data files |
Prompts (pre-built context bundles):
Prompt | Description |
| Fetches the 3-day forecast, geomagnetic forecast, forecast discussion, SGARF, and advisory outlook — combined into one block |
| Fetches the NOAA Planetary K-index (3-hour) and daily geomagnetic indices |
| Fetches the Kyoto Dst index (hourly) with an interpretation guide prepended |
Related MCP server: mcp-noaa-swpc
All data comes from NOAA SWPC's public data server:
Data: https://services.swpc.noaa.gov (JSON + text files, no API key required)
Product info: https://www.swpc.noaa.gov/products-and-data
No authentication is required. Data is provided by NOAA as a public service.
Python 3.14+
uv (recommended) or pip
git clone https://github.com/JimFlannery/space-weather-data-mcp.git
cd space-weather-data-mcp
uv syncAdd to your claude_desktop_config.json:
{
"mcpServers": {
"spaceweather": {
"command": "uv",
"args": [
"run",
"--directory",
"/absolute/path/to/space-weather-data-mcp",
"main.py"
]
}
}
}Config file locations:
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Add to your VS Code settings.json:
{
"mcp.servers": {
"spaceweather": {
"command": "uv",
"args": [
"run",
"--directory",
"/absolute/path/to/space-weather-data-mcp",
"main.py"
]
}
}
}Run the MCP Inspector to test tools and prompts interactively:
uv run mcp dev main.pyOnce connected to an MCP client, you can ask things like:
"What is the current space weather forecast?"
"Is there a geomagnetic storm in progress? Check the Kp index."
"What are today's active solar regions and their flare probabilities?"
"Fetch the latest GOES X-ray flux and classify any solar flares."
"What does a Kp of 7 mean for power grids?"
"Show me the Dst index and explain whether we're in a storm's main phase or recovery phase."
Scale | Measures | Range | Storm starts at |
G (Geomagnetic) | Kp index | G1–G5 | G1 (Kp = 5) |
S (Solar Radiation) | ≥10 MeV proton flux | S1–S5 | S1 (10 pfu) |
R (Radio Blackout) | X-ray flux (0.1–0.8 nm) | R1–R5 | R1 (M1 flare) |
Solar flares: A → B → C → M → X (each class is 10× stronger; X-class is open-ended).
Use the get_space_weather_scales tool for the full threshold and effects table.
MIT — see LICENSE.
Fetch the full description of a SWPC product from the NOAA website.
Use list_products() to find product slugs. This tool fetches the live product page from www.swpc.noaa.gov and returns its explanatory text — useful for detailed interpretation guidance, methodology, and caveats.
Args: product_slug: The product URL slug, e.g. "planetary-k-index", "goes-x-ray-flux", "wsa-enlil-solar-wind-prediction".
Returns: Plain text extracted from the product's NOAA web page.
Inputs: product_slug (required). Returns: result
Fetch the content of a file from the SWPC data server.
JSON files are returned as parsed objects; all other files (plain text, etc.) are returned as a string.
Args: path: File path relative to the server root, e.g. "json/solar_regions.json" or "text/3-day-forecast.txt".
Returns: Parsed JSON (dict or list) for .json files, plain text string otherwise.
Inputs: path (required).
Return field definitions and interpretation guidance for a known data file.
Use this tool before calling fetch_file() to understand what the data means, what each field represents, and how to interpret the values.
Args: path: The file path as used with fetch_file(), e.g. "json/planetary_k_index_1m.json" or "json/goes/primary/xrays-1-day.json".
Returns: A dict with description, fields, interpretation, and related files. If the path is not in the guide, returns a list of known paths.
Inputs: path (required). Returns: object
Return the NOAA space weather scales and solar flare classification system.
Call this tool to understand how to interpret space weather severity. It returns:
The three NOAA scales used for all space weather products: G (Geomagnetic storms, Kp-based, 1–5) S (Solar Radiation Storms, proton flux-based, 1–5) R (Radio Blackouts, X-ray flux-based, 1–5)
Solar flare X-ray classification (A/B/C/M/X) with flux thresholds and the mapping to R-scale radio blackout levels.
Returns: Dict with keys "noaa_scales" and "solar_flare_classes".
Inputs: no named parameters. Returns: object
List files and subdirectories at a path on the SWPC data server.
The server is organised as a browsable file tree rooted at https://services.swpc.noaa.gov. Top-level directories include json/, text/, products/, images/, experimental/, netcdf/, and static/.
Args: path: Directory path to list, e.g. "json/", "json/goes/", "text/". Leave empty (or pass "") to list the root.
Returns: A dict with two keys: "directories": list of subdirectory names (without trailing slash) "files": list of file names
Inputs: path. Returns: object
Return a curated map of notable paths and files on the SWPC data server.
Use this tool first to orient yourself before calling list_directory or fetch_file. The returned map groups paths by top-level directory and highlights commonly useful files.
Returns: A dict describing the server layout and selected files of interest.
Inputs: no named parameters. Returns: object
List SWPC space weather products, optionally filtered by category.
Each product entry includes its name, a description, and the data file paths on the SWPC data server where its data can be fetched.
Available categories: forecasts, reports, models, observations, summaries, alerts, experimental
Args: category: Optional category name to filter by (case-insensitive). Pass "" or omit to return all categories.
Returns: Dict mapping category names to lists of product dicts, each with keys: slug, name, description, data_paths.
Inputs: category. Returns: object
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 7 tools
Each tool serves a distinct role: browsing directories, fetching files, orienting via curated paths, explaining scales, listing products, describing products, and explaining data formats. No two tools have overlapping purposes.
All tool names follow a consistent verb_noun pattern (list_directory, fetch_file, list_known_paths, get_space_weather_scales, list_products, describe_product, get_data_file_info) with clear verbs and nouns.
Seven tools is a well-scoped set for a data server browser and fetcher, covering navigation, fetching, and interpretation without redundancy or bloat.
The tool set covers the full workflow: orienting (list_known_paths), browsing (list_directory), fetching (fetch_file), interpreting data (get_data_file_info, get_space_weather_scales), and discovering/understanding products (list_products, describe_product). No obvious gaps exist.
Space weather: Kp index, solar flare flux, alerts. $0.01/query, free testnet funds.
NOAA SWPC space weather: storm scales, Kp index, aurora forecasts, solar wind, activity, alerts.
Space weather: Kp index, NOAA 3-day geomagnetic forecast, solar flares, aurora visibility.
US NWS weather alerts and 5-day forecasts for AI agents. $0.01 per call.
