mcpField
C
Celestrak

Celestrak

Remote
pipeworx.ioScience & Education0Updated 5d ago

About Celestrak

Celestrak exposes CelesTrak’s satellite orbital catalog through MCP for catalog lookup and orbital-data analysis. It retrieves TLE / GP parameters by NORAD ID, name, or group, but does not provide live position tracking.

Key features

  1. 01Look up orbital parameters by NORAD ID
  2. 02Search the satellite catalog by name
  3. 03Retrieve orbital data for a satellite group
  4. 04Return derived values such as orbital period

Use cases

  1. 01Check orbital elements for the ISS or Hubble
  2. 02Search for Starlink or GPS satellites
  3. 03Retrieve the catalog for weather satellites

MCP support

It provides satellite-catalog tools to MCP clients through the Pipeworx gateway or as a local stdio MCP server.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://gateway.pipeworx.io/celestrak/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

mcp-celestrak

CelesTrak MCP — satellite orbital elements (TLE / GP data) for any tracked object.

Part of Pipeworx — an MCP gateway connecting AI agents to 1875+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.

Tools

ToolDescription
get_satelliteGet satellite orbital elements (TLE / GP data) for a single object by NORAD catalog ID. Returns orbital parameters: inclination, eccentricity, mean motion, RAAN, argument of perigee, epoch, and derived orbital period in minutes. norad_id 25544 = ISS, 20580 = Hubble. This is the orbital catalog, not live position tracking.
search_by_nameSearch the satellite catalog by name substring and return matching orbital elements (TLE / GP data). e.g. "STARLINK", "NOAA", "GPS". Returns up to 50 matches with orbital parameters (inclination, eccentricity, period). Catalog/orbital data, not live tracking.
get_groupList orbital elements (TLE / GP data) for an entire CelesTrak group — e.g. the Starlink, GPS, or weather satellite catalog. Groups: "stations", "starlink", "gps-ops", "weather", "science", "geo", "active". Returns up to 100 satellites with orbital parameters (inclination, eccentricity, period). Catalog/orbital data, not live tracking.

Quick Start

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

{
  "mcpServers": {
    "celestrak": {
      "url": "https://gateway.pipeworx.io/celestrak/mcp"
    }
  }
}
What this endpoint actually serves

tools/list at https://gateway.pipeworx.io/celestrak/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 1875+ data sources. The only difference is which pack's tools are listed directly; ask_pipeworx reaches all of them from either one.

No MCP client? Call it over HTTP

curl -X POST https://gateway.pipeworx.io/v1/tools/get_satellite \
  -H 'Content-Type: application/json' \
  -d '{"norad_id":25544}'

No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/get_satellite. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.

Standalone (no gateway account)

This package also runs as a local stdio MCP server — no Pipeworx account, no gateway round-trip:

{
  "mcpServers": {
    "celestrak": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-celestrak"]
    }
  }
}

Or run it directly to confirm it starts:

npx -y @pipeworx/mcp-celestrak

It speaks MCP over stdin/stdout and answers initialize/tools/list/tools/call for only this pack's tools — none of the shared meta-tools the gateway connection above adds. Same source, same tools, no ask_pipeworx routing.

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 Celestrak data" })

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

More

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.