
A straightforward way to add live science data to your AI workflows. Exposes four NASA and USGS endpoints: ISS position tracking with coordinates and velocity, recent earthquake search by location and magnitude, air quality checks that return AQI and pollutant levels for major cities, and NASA's Astronomy Picture of the Day with images and explanations. Runs as a hosted service through Pipeworx's gateway, so no local setup or API keys needed. Useful when you're building agents that need real-time space or environmental data without managing multiple API integrations yourself.
Science MCP — free science data APIs
Part of Pipeworx — an MCP gateway connecting AI agents to 1476+ live data sources.
| Tool | Description |
|---|---|
get_iss_location | Fetch the International Space Station's current latitude, longitude, and Unix timestamp from the Open Notify API. No inputs required; returns a real-time position fix. |
get_earthquakes | Retrieve up to 20 globally recent earthquakes from the USGS FDSN service, filtered by lookback period (1–30 days, default 1) and minimum magnitude (default 4.0). Returns magnitude, location name, depth (km), coordinates, time, and tsunami warning flag. |
get_air_quality | Check current air quality at a latitude/longitude. Returns US AQI score and category plus PM2.5, PM10, ozone, NO2, and CO levels. |
get_apod | Get NASA's Astronomy Picture of the Day with image URL, title, and explanation. Optionally specify a date (e.g., '2024-01-15'). |
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"science": {
"url": "https://gateway.pipeworx.io/science/mcp"
}
}
}
tools/list at https://gateway.pipeworx.io/science/mcp returns the tools in the table
above plus the shared Pipeworx meta-tools — ask_pipeworx,
discover_tools, search_within, remember/recall and the rest of the
gateway-wide set. So the tool count you see is larger than this table: a
single-pack endpoint currently lists roughly 30 shared tools alongside the
pack's own. The connection's initialize response states its exact scope, and
is the authoritative answer for a given day.
This is deliberate, not multiplexing by accident. The meta-tools are what let a
scoped connection answer a question this pack does not cover — via
ask_pipeworx, which routes across the whole catalog — without you adding a
second MCP server. There is currently no way to mount a pack endpoint without
them; if the extra schemas cost you more context than the routing is worth,
connect to the full gateway once rather than to several pack endpoints.
Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}
Both URLs reach the same gateway and the same 1476+ data sources. The
only difference is which pack's tools are listed directly; ask_pipeworx
reaches all of them from either one.
Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:
ask_pipeworx({ question: "your question about Science data" })
The gateway picks the right tool and fills the arguments automatically.
MIT