Astrodynamics MCP Server

Astrodynamics MCP server: TLE/SGP4, Lambert, access windows, porkchop, B-plane targeting.

Remote serverstreamable-httpPython

What is the Astrodynamics MCP server?

Astrodynamics MCP server: TLE/SGP4, Lambert, access windows, porkchop, B-plane targeting. The astrodynamics mcp server wraps that behind the Model Context Protocol, so an assistant can use it through 14 defined tools rather than through you.

What it actually does

A Model Context Protocol server that gives any MCP-capable LLM client (Claude Code, Cursor, ChatGPT desktop, custom agents) authoritative astrodynamics tools: TLE/SGP4 propagation, Lambert solving, ground-station access, time-scale and coordinate-frame conversions, porkchop scans, B-plane targeting, satellite metadata, and — with optional extras — full NASA GMAT mission execution ([gmat]), NASA SPICE / NAIF kernel queries ([spice]), and trajectory visualisation ([viz]).

Its toolset

Everything the assistant can do here goes through one of these:

  • tle_lookup — Fetch current TLEs by NORAD ID, name, or group — from CelesTrak (default) or Space-Track
  • sgp4_propagate — Propagate TLEs across UTC ISO 8601 epochs in TEME / ICRF / GCRS / ITRS / CIRS
  • lambert_solve — Solve Lambert's problem; multi-rev solutions enumerated; two-impulse Δv on demand
  • access_windows — Ground-station / observer access intervals over a window, with AOS / LOS / peak elevation
  • time_convert — UTC / TAI / TT / TDB / UT1 / GPS / TCB / TCG conversions across ISO / JD / MJD / J2000-seconds / Unix
  • frame_transform — State-vector transforms across ICRF / ITRS / GCRS / TEME / CIRS / TIRS / IAU body-fixed frames
  • porkchop — (depart × arrive) Δv / C3 grid for interplanetary transfers, ASCII contour, summary or full output
  • bplane_target — B-plane element calculation and impulsive targeting for hyperbolic flybys
  • satellite_metadata — Physical & provenance metadata (mass, dimensions, COSPAR ID, launch, operator, decay status) for a NORAD ID
  • gmat_run_mission — Run a complete GMAT mission; returns a parsed summary, report data, and pointers to large outputs
  • gmat_sweep — Parameter sweeps and Monte Carlo (grid / samples / Monte Carlo / Latin hypercube) over a mission
  • gmat_execute_script — Escape hatch — run raw GMAT script text and return its reports verbatim; engine errors come back as data

Adding it to your client

Being a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.

When to reach for it

Plenty of developer tooling servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Astrodynamics's toolset — tle_lookup, sgp4_propagate, lambert_solve and 11 more — is a fair guide to whether it matches your workflow. It is maintained by astro-tools; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Caveats

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Astrodynamics.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the astrodynamics mcp server does with a few real requests.

Available tools

ToolWhat it does
tle_lookupFetch current TLEs by NORAD ID, name, or group — from CelesTrak (default) or Space-Track.
sgp4_propagatePropagate TLEs across UTC ISO 8601 epochs in TEME / ICRF / GCRS / ITRS / CIRS.
lambert_solveSolve Lambert's problem; multi-rev solutions enumerated; two-impulse Δv on demand.
access_windowsGround-station / observer access intervals over a window, with AOS / LOS / peak elevation.
time_convertUTC / TAI / TT / TDB / UT1 / GPS / TCB / TCG conversions across ISO / JD / MJD / J2000-seconds / Unix.
frame_transformState-vector transforms across ICRF / ITRS / GCRS / TEME / CIRS / TIRS / IAU body-fixed frames.
porkchop(depart × arrive) Δv / C3 grid for interplanetary transfers, ASCII contour, summary or full output.
bplane_targetB-plane element calculation and impulsive targeting for hyperbolic flybys.
satellite_metadataPhysical & provenance metadata (mass, dimensions, COSPAR ID, launch, operator, decay status) for a NORAD ID.
gmat_run_missionRun a complete GMAT mission; returns a parsed summary, report data, and pointers to large outputs.
gmat_sweepParameter sweeps and Monte Carlo (grid / samples / Monte Carlo / Latin hypercube) over a mission.
gmat_execute_scriptEscape hatch — run raw GMAT script text and return its reports verbatim; engine errors come back as data.
gmat_validate_scriptParse-validate a script without running it; returns errors, warnings, and the resource/command structure.
gmat_read_run_artefactRead the raw text of a file produced by a prior run (ephemerides, reports too large to inline).

How to install the Astrodynamics MCP server

{
  "mcpServers": {
    "astrodynamics": {
      "command": "uvx",
      "args": ["astrodynamics-mcp"]
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Example prompts to try

  • Use Astrodynamics to tle lookup.
  • Use Astrodynamics to sgp4 propagate.
  • Use Astrodynamics to lambert solve.

Frequently asked questions

It connects Astrodynamics to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (tle_lookup, sgp4_propagate, lambert_solve, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Astrodynamics directly.