Astronomy Oracle MCP server

Astronomy Oracle

Accurate astronomical catalog data and observing session planner for LLM assistants. Stops hallucinated magnitudes, coordinates, and visibility.

Features

• 3 tools for object lookup, catalog search, and observing session planning
• 13,000+ deep-sky objects from the OpenNGC catalog (NGC, IC, Messier, and addendum objects)
• Deterministic astronomy math — Julian dates, sidereal time, alt/az conversion, rise/transit/set times
• Zero network dependency — all data is bundled, all calculations are local

Install

Run directly with npx:

npx astronomy-oracle

Or install globally:

npm install -g astronomy-oracle

Configuration

Claude Desktop

Add to your claudedesktopconfig.json:

{
  "mcpServers": {
    "astronomy-oracle": {
      "command": "npx",
      "args": ["-y", "astronomy-oracle"]
    }
  }
}

Claude Code

claude mcp add astronomy-oracle -- npx -y astronomy-oracle

Tool Reference

lookup_object

Look up a celestial object by Messier number, NGC/IC designation, or common name. Optionally compute visibility from a given location and time.

{
  "name": "lookup_object",
  "arguments": {
    "name": "M31",
    "latitude": 51.5,
    "longitude": -0.1,
    "date": "2025-06-15T22:00:00Z"
  }
}

Returns detailed object data: type, coordinates (RA/Dec), magnitude, angular size, surface brightness, Hubble type, cross-references, and (when location is provided) current altitude/azimuth with rise/transit/set times.

search_objects

Search and filter the catalog by type, constellation, magnitude range, angular size, or catalog membership.

{
  "name": "search_objects",
  "arguments": {
    "type": "PN",
    "constellation": "Lyr",
    "maxMagnitude": 12.0,
    "limit": 10
  }
}

Returns a formatted table of matching objects sorted by brightness. Supports filtering by object type (Galaxy, Planetary Nebula, Open Cluster, etc.), constellation, magnitude range, minimum angular size, and catalog (Messier, Caldwell, NGC, IC).

plan_session

Generate an observing session plan for a given location and date. Returns the best objects to observe grouped by time window.

{
  "name": "plan_session",
  "arguments": {
    "latitude": 40.7,
    "longitude": -74.0,
    "date": "2025-03-20",
    "minAltitude": 20,
    "maxMagnitude": 10.0,
    "types": ["G", "PN", "GCl"]
  }
}

Returns objects grouped into three windows (evening, midnight, pre-dawn), scored by observability based on altitude, magnitude, and angular size.

Data Sources

Shortened. The full README is on GitHub.