Earthdata MCP Server provides a bridge between AI assistants and NASA's Earthdata platform, enabling search and retrieval of Earth science datasets and data granules. Built with FastMCP, it exposes two main tools: search_earth_datasets for discovering datasets based on keywords, temporal ranges, and geographic boundaries, and search_earth_datagranules for retrieving specific data granules by dataset short name. This implementation is particularly valuable for researchers, scientists, and analysts who need to access NASA Earth observation data directly through conversational AI interfaces without switching to specialized data portals.
Nessuna recensione ancora. Sii il primo a recensire!
Accedi per unirti alla conversazione
Highlight AISearch for datasets on NASA Earthdata. Input: search_keywords (str), count (int), temporal (tuple), bounding_box (tuple). Returns: List of dataset abstracts.
Search for data granules on NASA Earthdata. Input: short_name (str), count (int), temporal (tuple), bounding_box (tuple). Returns: List of data granules.
Search and optionally download granules with explicit modes. Input: folder_name (str), short_name (str), count (int), temporal (tuple), bounding_box (tuple), mode (str), max_manifest_items (int). Requires NASA Earthdata Login credentials.
Generates a workflow that starts with download_earth_data_granules in script mode. Intended to be executed in a composed notebook/runtime stack (via mcp-compose).
Search for datasets related to sea level rise worldwide. Input: start_year (int), end_year (int). Returns: Prompt correctly formatted.
To ask about the format of the datasets. Returns: Prompt correctly formatted.
