io.github.huangzesen/xhelio-spice
Auto-managed SPICE kernels for heliophysics missions. Enables querying spacecraft positions, trajectories, and coordinate transforms via natural language.
README
xhelio-spice
Spacecraft ephemeris made easy — auto-managed SPICE kernels for heliophysics missions.
xhelio-spice wraps SpiceyPy with automatic kernel download, caching, and loading. Ask for a spacecraft position and xhelio-spice handles the rest: downloading the right NAIF kernels, loading them in the correct order, and returning results as Python dicts or pandas DataFrames.
Installation
pip install xhelio-spice
For MCP server support (Claude Desktop, Claude Code, Cursor, etc.):
pip install xhelio-spice[mcp]
Quick Start
from xhelio_spice import get_position, get_trajectory
# Where is Parker Solar Probe right now?
pos = get_position("PSP", observer="SUN", time="2024-01-15", frame="ECLIPJ2000")
print(f"PSP is {pos['r_au']:.3f} AU from the Sun")
# Get a month of trajectory data as a DataFrame
df = get_trajectory(
"PSP", observer="SUN",
time_start="2024-01-01", time_end="2024-01-31",
step="1h", frame="ECLIPJ2000",
)
print(df[["r_au"]].describe())
Kernels are automatically downloaded from NAIF on first use and cached in ~/.xhelio_spice/kernels/.
Supported Missions
With SPICE Kernels (auto-downloaded)
- PSP (Parker Solar Probe) — 2018-2030
- Solar Orbiter (SOLO) — 2020-2030
- STEREO-A — 2017-2031
- Juno — 2011-present (updated regularly)
- Voyager 1/2 — 1981-2100 / 1989-2100
- New Horizons — 2019-2030
NAIF IDs Only (no auto-download yet)
- ACE, Wind, DSCOVR, MMS (1-4) — no public SPK kernels exist
- Cassini, MAVEN — require multi-segment kernel loading (planned)
- Galileo, Pioneer 10/11, Ulysses, MESSENGER, STEREO-B
Natural Bodies
Sun, Earth, Moon, Mercury, Venus, Mars, Jupiter, Saturn, Uranus, Neptune, Pluto
API Reference
Position & Trajectory
from xhelio_spice import get_position, get_trajectory, get_state
# Single position
pos = get_position("ACE", observer="EARTH", time="2024-06-01", frame="GSE")
# Full state (position + velocity)
state = get_state("PSP", observer="SUN", time="2024-01-15", frame="ECLIPJ2000")
# Trajectory timeseries (returns pandas DataFrame)
df = get_trajectory(
"Cassini", observer="SATURN",
time_start="2010-01-01", time_end="2010-12-31",
step="6h", frame="ECLIPJ2000",
include_velocity=True,
)
Coordinate Transforms
from xhelio_spice import transform_vector, list_available_frames
# J2000 to Ecliptic
v_ecl = transform_vector([1.0, 0.0, 0.0], "2024-01-15", "J2000", "ECLIPJ2000")
# RTN transform (requires spacecraft)
v_rtn = transform_vector(
[5.0, -3.0, 1.0], "2024-01-15",
from_frame="ECLIPJ2000", to_frame="RTN",
spacecraft="PSP",
)
# List all frames
print(list_available_frames())
Mission Registry
from xhelio_spice import resolve_mission, list_supported_missions
# Resolve name aliases
naif_id, key = resolve_mission("Parker Solar Probe") # -> (-96, "PSP")
# List all spacecraft
missions = list_supported_missions()
Kernel Management
from xhelio_spice import get_kernel_manager
km = get_kernel_manager()
km.ensure_mission_kernels("PSP") # Download + load
print(km.get_cache_info()) # Cache stats
km.unload_all() # Free memory
Configuration
| Method | Description |
|---|---|
XHELIO_SPICE_KERNEL_DIR env var |
Override kernel cache directory |
KernelManager(kernel_dir=...) |
Per-instance override |
| Default | ~/.xhelio_spice/kernels/ |
MCP Server
xhelio-spice includes an MCP server for LLM tool use:
# Run directly
xhelio-spice-mcp
# Or via Python
python -m xhelio_spice.server
Claude Desktop Configuration
Add to claude_desktop_config.json:
{
"mcpServers": {
"xhelio-spice": {
"command": "xhelio-spice-mcp"
}
}
}
Available MCP Tools
| Tool | Description |
|---|---|
get_ephemeris |
Position/velocity — single time (inline) or timeseries (CSV) |
compute_distance |
Distance between two bodies |
transform_coordinates |
Coordinate frame transform |
list_spice_missions |
Supported missions |
list_coordinate_frames |
Available frames with descriptions |
manage_kernels |
Kernel cache management |
MCP smoke test
For a CI-safe MCP check that does not request kernel downloads, run:
uv run --extra mcp python scripts/smoke_mcp_list_tools.py --json
The smoke starts the stdio server with an isolated temporary kernel cache, runs
MCP initialize + list_tools, and verifies the advertised tool names.
License
MIT
<!-- mcp-name: io.github.huangzesen/xhelio-spice -->
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.