Earthdata MCP Server logo

Earthdata MCP Server

by Datalayer

Earthdata MCP Server is a Model Context Protocol (MCP) server implementation that provides tools to interact with NASA Earth Data. It enables efficient dataset discovery and retrieval for Geospatial analysis.

View on GitHub

Last updated: N/A

What is Earthdata MCP Server?

Earthdata MCP Server is a server implementation based on the Model Context Protocol (MCP) designed to facilitate interaction with NASA Earth Data. It provides tools for discovering and retrieving datasets and data granules relevant to geospatial analysis.

How to use Earthdata MCP Server?

The server can be used with Claude Desktop by adding the provided configuration to claude_desktop_config.json. It exposes two tools: search_earth_datasets for finding datasets and search_earth_datagranules for finding data granules. These tools accept search keywords, counts, temporal ranges, and bounding boxes as input.

Key features of Earthdata MCP Server

  • Dataset discovery on NASA Earthdata

  • Data granule retrieval

  • Integration with Model Context Protocol (MCP)

  • Support for temporal and spatial filtering

  • Easy integration with Claude Desktop

Use cases of Earthdata MCP Server

  • Analyzing sea level rise

  • Environmental monitoring

  • Climate change research

  • Geospatial data analysis

FAQ from Earthdata MCP Server

What is MCP?

MCP stands for Model Context Protocol. It is a protocol that provides a standardized way for applications to interact with data and models.

What kind of data can I access with this server?

You can access datasets and data granules from NASA Earthdata related to various Earth science domains.

How do I specify a temporal range for my search?

The temporal range should be provided as a tuple in the format (date_from, date_to).

How do I specify a bounding box for my search?

The bounding box should be provided as a tuple in the format (lower_left_lon, lower_left_lat, upper_right_lon, upper_right_lat).

Can I use this server outside of Claude Desktop?

Yes, the server can be used independently as long as you can interact with it using the Model Context Protocol. The README shows how to build and run it using Docker.