Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@space-mcp-server What is the Astronomy Picture of the Day?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP server giving AI agents access to NASA and space/astronomy data — APOD, Mars rover photos, near-Earth asteroids, exoplanets, Earth imagery, natural events, and space weather.
Tool | Description |
| NASA's Astronomy Picture of the Day (APOD) |
| Search NASA's 140,000+ image/video library |
| Query 5,000+ confirmed exoplanets |
| Solar flares, CMEs, geomagnetic storms (DONKI) |
| Real photos from Curiosity, Perseverance, Opportunity, Spirit |
| Rover mission status, cameras, photo counts |
| Track asteroids approaching Earth (NeoWs) |
| Orbital data and close approaches for specific asteroids |
| Full-Earth photos from DSCOVR satellite (EPIC) |
| Active wildfires, volcanoes, storms worldwide (EONET) |
Related MCP server: NASA-MCP
git clone https://github.com/AiAgentKarl/space-mcp-server.git
cd space-mcp-server
python -m venv .venv
.venv/Scripts/activate # Windows
# source .venv/bin/activate # Linux/Mac
pip install -e .cp .env.example .env
# Edit .env and add your NASA API key (optional, DEMO_KEY works out of the box)Get a free API key at https://api.nasa.gov/ for higher rate limits.
space-mcp
# or
python -m src.serverAdd to your .mcp.json:
{
"mcpServers": {
"space": {
"type": "stdio",
"command": "path/to/.venv/Scripts/python.exe",
"args": ["-m", "src.server"],
"env": {
"NASA_API_KEY": "your-api-key-here"
}
}
}
}API | Key Required | Rate Limit |
NASA API (APOD, Mars, NeoWs, DONKI) | Yes (DEMO_KEY works) | 30/hour (DEMO), 1000/hour (registered) |
No | No limit | |
No | No limit | |
No | No limit | |
No | No limit |
src/
├── server.py # FastMCP server entry point
├── config.py # Settings & environment variables
├── analytics.py # Usage tracking
├── clients/
│ ├── nasa.py # NASA API (APOD, Mars, NeoWs, DONKI)
│ ├── epic.py # EPIC Earth imagery
│ ├── eonet.py # EONET natural events
│ ├── nasa_images.py # NASA Image Library
│ └── exoplanet.py # Exoplanet Archive
└── tools/
├── astronomy.py # APOD, image search, exoplanets, space weather
├── mars.py # Mars rover photos & info
├── asteroids.py # Near-Earth objects & asteroid details
└── earth.py # EPIC imagery & natural eventsCategory | Servers |
🔗 Blockchain | |
🌍 Data | Weather · Germany · Agriculture · Space · Aviation · EU Companies |
🔒 Security | |
🤖 Agent Infra | Memory · Directory · Hub · Reputation |
🔬 Research |
MIT
Detaillierte Informationen zu einem bestimmten Asteroiden.
Zeigt Orbitalparameter, alle nahen Vorbeiflüge und physische Daten.
Args: asteroid_id: NEO-Referenz-ID (z.B. "3542519" für Bennu)
Inputs: asteroid_id (required).
Astronomy Picture of the Day (APOD) abrufen.
NASAs berühmtes tägliches Astronomiebild mit Erklärung. Ohne Parameter: heutiges Bild. Mit Datum: bestimmter Tag. Mit count: mehrere zufällige Bilder.
Args: date: Bestimmtes Datum im Format YYYY-MM-DD (optional) count: Anzahl zufälliger Bilder (1-100, optional)
Inputs: date, count.
Echte Fotos der Erde von NASAs DSCOVR-Satellit (EPIC-Kamera).
Liefert Bilder der ganzen Erde aus 1,5 Millionen km Entfernung am Lagrange-Punkt L1. Zeigt Wolken, Kontinente und Ozeane.
Args: date: Bestimmtes Datum YYYY-MM-DD (optional, Standard: neueste) limit: Maximale Anzahl Bilder (Standard: 5, Maximum: 20)
Inputs: date, limit.
Bestätigte Exoplaneten aus NASAs Exoplanet Archive suchen.
Durchsucht die Datenbank mit über 5.000 bestätigten Exoplaneten.
Args: discovery_year: Entdeckungsjahr filtern (z.B. 2024) discovery_method: Entdeckungsmethode (z.B. "Transit", "Radial Velocity") min_mass: Mindestmasse in Jupitermassen (optional) max_mass: Maximalmasse in Jupitermassen (optional) limit: Maximale Anzahl Ergebnisse (Standard: 20, Maximum: 50)
Inputs: discovery_year, discovery_method, min_mass, max_mass, +1 more.
Missionsinformationen eines Mars-Rovers abrufen.
Zeigt Status, Landedatum, Gesamtanzahl Fotos und Kamera-Liste.
Args: rover: Rover-Name — "curiosity", "perseverance", "opportunity" oder "spirit"
Inputs: rover.
Fotos von Mars-Rovern abrufen.
Zeigt echte Fotos von der Marsoberfläche. Ohne sol/earth_date: neueste verfügbare Fotos.
Args: rover: Rover-Name — "curiosity", "perseverance", "opportunity" oder "spirit" sol: Mars-Sol (Marstag seit Landung, z.B. 1000) earth_date: Erddatum im Format YYYY-MM-DD (alternativ zu sol) camera: Kamera-Kürzel (z.B. "FHAZ", "RHAZ", "MAST", "NAVCAM", "CHEMCAM") limit: Maximale Anzahl Fotos (Standard: 10, Maximum: 25)
Inputs: rover, sol, earth_date, camera, +1 more.
Aktuelle Naturereignisse weltweit abrufen (EONET).
Zeigt aktive Waldbrände, Vulkanausbrüche, Stürme, Überschwemmungen und andere Naturkatastrophen mit Koordinaten und Zeitstempel.
Args: category: Kategorie — "wildfires", "volcanoes", "severeStorms", "seaLakeIce", "earthquakes", "floods", "landslides" (optional) status: "open" (aktive Events) oder "closed" (beendete) days: Events der letzten N Tage (optional) limit: Maximale Anzahl Events (Standard: 20, Maximum: 50)
Inputs: category, status, days, limit.
Erdnahe Asteroiden in einem Zeitraum abrufen (NeoWs).
Zeigt Asteroiden die der Erde nahe kommen, mit Größe, Geschwindigkeit, Entfernung und Gefahrenbewertung.
Args: start_date: Startdatum im Format YYYY-MM-DD end_date: Enddatum im Format YYYY-MM-DD (optional, max. 7 Tage Spanne)
Inputs: start_date (required), end_date.
Aktuelle Weltraumwetter-Daten von NASAs DONKI abrufen.
Zeigt Sonneneruptionen, koronale Massenauswürfe (CME) und geomagnetische Stürme. Wichtig für Satellitenoperationen und Polarlicht-Vorhersagen.
Args: start_date: Startdatum YYYY-MM-DD (Standard: letzte 7 Tage) end_date: Enddatum YYYY-MM-DD (optional) event_type: "all", "cme" (Massenauswürfe), "flare" (Eruptionen) oder "storm" (geomagnetische Stürme)
Inputs: start_date, end_date, event_type.
Nutzungsstatistiken des MCP-Servers abrufen.
Zeigt: Gesamtanzahl Tool-Aufrufe, Aufrufe pro Tool, erster und letzter Aufruf.
Inputs: no named parameters.
NASAs Bild- und Video-Bibliothek durchsuchen (140.000+ Medien).
Findet Bilder, Videos und Audiodateien aus NASAs gesamtem Archiv.
Args: query: Suchbegriff (z.B. "apollo 11", "mars landing", "hubble nebula") media_type: Medientyp — "image", "video" oder "audio" (optional) year_start: Ergebnisse ab diesem Jahr (optional) year_end: Ergebnisse bis zu diesem Jahr (optional) page_size: Anzahl Ergebnisse (Standard: 10, Maximum: 100)
Inputs: query (required), media_type, year_start, year_end, +1 more.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 11 tools
Each tool targets a distinct space-related domain (asteroids, APOD, Earth imagery, exoplanets, Mars rovers, natural events, NEO, space weather, usage stats, NASA image search). No two tools have overlapping purposes.
All tools follow a consistent verb_noun pattern in snake_case, with most using 'get_'. The exception is 'search_nasa_images' which uses 'search_' instead of 'get_', a minor deviation.
With 11 tools, the server covers a broad range of space data without being overwhelming. Each tool serves a clear, non-redundant purpose, making the count appropriate for the scope.
The tool set covers major NASA data sources (APOD, Mars photos, NEO, space weather, natural events, image search) but lacks coverage of satellite tracking, deep space missions, or planetary facts. Minor gaps but functional for common tasks.
Hosted MCP server for live public-data APIs and Skills for AI agents.
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
Real-time planetary signal engine and Model Context Protocol (MCP) server for autonomous AI agents.
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
