Odel
Nasa

Nasa

@pipeworx-ioTypeScriptMITUpdated 1w ago

NASA MCP — wraps NASA Open APIs (api.nasa.gov)

Server endpointStreamable HTTPNo authProbed

This is the third-party server itself — Odel doesn't run it. Hitting this URL directly talks straight to the upstream server with no auth or proxying. Connect through Odel to front it with managed auth.

mcp-nasa

NASA MCP — wraps NASA Open APIs (api.nasa.gov)

Part of Pipeworx — an MCP gateway connecting AI agents to 1476+ live data sources.

Tools

ToolDescription
get_apodGet the NASA Astronomy Picture of the Day with explanation. Optionally specify a date. Example: get_apod({ date: "2024-01-15", _apiKey: "DEMO_KEY" })
get_asteroidsGet near-Earth asteroids approaching within a date range (max 7 days). Returns size, velocity, and miss distance. Example: get_asteroids({ start_date: "2024-01-01", end_date: "2024-01-07", _apiKey: "DEMO_KEY" })
get_mars_photos"Show me photos from the Mars rover" / "Perseverance images from sol 1000" / "latest pictures from Mars" — raw images from NASA's Perseverance rover (Mars 2020), straight off the mars.nasa.gov feed. Filter by Martian sol and by camera. Returns image URLs at four resolutions, the sol, the UTC and Mars-local capture times, and the camera instrument. Keyless. Covers Perseverance only — Curiosity, Opportunity and Spirit have no live public image feed. Example: get_mars_photos({ sol: 1000, camera: "NAVCAM_LEFT" })
search_nasa_imagesSearch the NASA Image and Video Library for images/videos of any subject — planets, missions, astronauts, launches, galaxies, etc. PREFER for "NASA photos of Jupiter", "images of the Apollo 11 mission", "pictures of a nebula". Returns title, description, date, NASA ID, media type, and a thumbnail URL. Keyless.
get_solar_flaresGet recent solar flare events from NASA DONKI space-weather data. Returns each flare's class (e.g. C4.0, M1.8, X1.2), begin/peak/end times, source region, and active region number. Use for "recent solar flares", "is there solar activity / a solar storm", space-weather questions.

Quick Start

Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):

{
  "mcpServers": {
    "nasa": {
      "url": "https://gateway.pipeworx.io/nasa/mcp"
    }
  }
}

What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/nasa/mcp returns the tools in the table above plus the shared Pipeworx meta-toolsask_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.

Using with ask_pipeworx

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 Nasa data" })

The gateway picks the right tool and fills the arguments automatically.

More

License

MIT