NASA-MCP. Integration via MCP with NASA APIs
NASA is the National Aeronautics and Space Administration of the United States.
NASA-MCP allows you to retrieve astronomical data, space weather information, Earth imagery, and more from NASA's APIs directly from Claude AI and other MCP compatible clients, using the Model Context Protocol (MCP).
NASA-MCP is an MCP server that exposes tools enabling LLMs to query data from various NASA APIs, including APOD (Astronomy Picture of the Day), Asteroids NeoWs, DONKI (Space Weather Database), Earth imagery, EPIC (Earth Polychromatic Imaging Camera), and Exoplanet data.
It includes secure handling of API keys and proper error management for all API requests.
Key Features
- Access to Astronomy Picture of the Day (APOD) with explanations and imagery
- Query Near Earth Objects data and asteroid information
- Retrieve Space Weather data from DONKI, including solar flares, geomagnetic storms, and more
- Get Earth imagery from Landsat 8 satellite for specific coordinates
- Access EPIC camera images showing the full Earth disk
- Query the Exoplanet Archive database for information about planets outside our solar system
Installation
Installing via Smithery
To install NASA API Integration Server for Claude Desktop automatically via Smithery:
Install with uv
Prerequisites
- Python 3.10 or higher
- uv package manager
Installing uv
The first step is to install uv
, a package manager for Python.
It can be installed from the command line.
On macOS and Linux:
On Windows:
You can also install it with pip:
For more information about installing uv, visit the uv documentation.
Integration with clients like Claude for Desktop
Once uv is installed, you can use the MCP server from any compatible client such as Claude for Desktop, in which case the steps to follow are:
- Go to Claude > Settings > Developer > Edit Config >
claude_desktop_config.json
- Add the following block inside
"mcpServers"
:
- Get a free API key from NASA at: https://api.nasa.gov/
- Replace
YOUR_NASA_API_KEY
with your actual API key (leave the quotes). You can also use "DEMO_KEY" for limited testing. - If you already have another MCP server configured, separate each with a comma
,
.
In general, to integrate it into any other MCP-compatible client such as Cursor, CODEGPT, or Roo Code, simply go to the MCP server configuration of your client and add the same code block.
Usage Examples
Once properly configured, you can ask things like:
- "Show me today's astronomy picture of the day"
- "Find asteroids that will pass near Earth in the next week"
- "Get information about solar flares from January 2023"
- "Show me Earth imagery for coordinates 29.78, -95.33"
- "Find exoplanets in the habitable zone"
DISTRIBUTIONS
Smithery
MCP Review
remote-capable server
The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.
Tools
Ein MCP-Server, der es LLMs ermöglicht, Daten von verschiedenen NASA-APIs abzufragen und so den Zugriff auf astronomische Daten, Weltraumwetterinformationen, Erdbilder und Exoplaneteninformationen direkt von kompatiblen KI-Clients aus zu ermöglichen.
Related Resources
Related MCP Servers
- AsecurityFlicenseAqualityAn MCP server that fetches real-time documentation for popular libraries like Langchain, Llama-Index, MCP, and OpenAI, allowing LLMs to access updated library information beyond their knowledge cut-off dates.Last updated -12
- AsecurityFlicenseAqualityA lightweight MCP server that provides a unified interface to various LLM providers including OpenAI, Anthropic, Google Gemini, Groq, DeepSeek, and Ollama.Last updated -6634
CMR Model Context Protocolofficial
AsecurityFlicenseAqualityAn MCP server that integrates AI retrievals with NASA's Common Metadata Repository (CMR), allowing users to search NASA's catalog of Earth science datasets through natural language queries.Last updated -14- -securityAlicense-qualityA server that integrates the MCP library with OpenAI's API, allowing users to interact with various tools, such as the weather tool, through natural language queries.Last updated -MIT License