Earthdata MCP Server

🚀 Earth Data MCP Server

The Earth Data MCP Server is an implementation of the Model Context Protocol (MCP) server, offering tools to interact with NASA Earth Data. It enables efficient dataset discovery and retrieval, suitable for geospatial analysis.

The following demonstration shows how to use this MCP server to search for datasets and data granules on NASA Earth Data, and download data using jupyter-earth-mcp-server for further analysis on jupyter-mcp-server.

🚀 Quick Start

Using with Claude Desktop

To use with Claude Desktop, add the following to your claude_desktop_config.json:

{
  "mcpServers": {
    "earthdata": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "datalayer/earthdata-mcp-server:latest"
      ]
    }
  }
}

If you are using Linux, start Claude with the following command:

make claude-linux

✨ Features

Tools

The server provides two tools:

search_earth_datasets

• Search for datasets on NASA Earth Data.
• Input:
  • search_keywords (str): Keywords for searching in dataset titles.
  • count (int): Number of datasets to return.
  • temporal (tuple): (Optional) Time range in the format (start date, end date).
  • bounding_box (tuple): (Optional) Bounding box in the format (lower left longitude, lower left latitude, upper right longitude, upper right latitude).
• Output: List of dataset summaries.

search_earth_datagranules

• Search for data granules on NASA Earth Data.
• Input:
  • short_name (str): Short name of the dataset.
  • count (int): Number of data granules to return.
  • temporal (tuple): (Optional) Time range in the format (start date, end date).
  • bounding_box (tuple): (Optional) Bounding box in the format (lower left longitude, lower left latitude, upper right longitude, upper right latitude).
• Output: List of data granules.

Prompts

1. sealevel_rise_dataset

   • Search for datasets related to global sea-level change.
   • Input:
     • start_year (int): Start year.
     • end_year (int): End year.
   • Output: List of relevant datasets.

2. precipitation_data

   • Search for datasets related to precipitation.
   • Input:
     • region (str): Region name.
     • time_range (tuple): Time range in the format (start date, end date).
   • Output: List of relevant datasets.

3. temperature_anomalies

   • Search for datasets related to temperature anomalies.
   • Input:
     • latitude (float): Latitude.
     • longitude (float): Longitude.
     • time_period (str): Time period, e.g., "annual" or "monthly".
   • Output: List of relevant datasets.

4. atmospheric_pressure

   • Search for datasets related to atmospheric pressure.
   • Input:
     • altitude (int): Altitude.
     • location (str): Location name.
     • season (str): Season, e.g., "summer" or "winter".
   • Output: List of relevant datasets.

5. ocean_currents

   • Search for datasets related to ocean currents.
   • Input:
     • ocean (str): Ocean name.
     • current_name (str): Current name.
     • depth (int): Depth.
   • Output: List of relevant datasets.

📦 Installation

Building Docker Image

If needed, you can build your own Docker image with the following command:

make build-docker

Alternatively, you can pull the pre-built image:

make pull-docker

📚 Documentation

Project Links

• GitHub Repository
• Docker Hub Image

📄 License

This project is licensed under the MIT License. See LICENSE for details.