Jupyter Earth MCP Server

🚀 Jupyter Earth MCP Server

Jupyter Earth MCP Server is a Docker-based tool for downloading and analyzing geoscience data in Jupyter Notebook. It supports downloading specified datasets from NASA Earth Data and provides integration with Claude Desktop.

🚀 Quick Start

Launch JupyterLab

1. Install the necessary dependencies:

pip install jupyter notebook requests

2. Start Jupyter Notebook:

jupyter notebook --ip=0.0.0.0 --port=8888

Configure the Docker Image

make build-docker

💻 Usage Examples

Integration with Claude Desktop

Configuration for Windows and macOS

{
  "mcpServers": {
    "jupyter-earth": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "SERVER_URL",
        "-e",
        "TOKEN",
        "-e",
        "NOTEBOOK_PATH",
        "datalayer/jupyter-earth-mcp-server:latest"
      ],
      "env": {
        "SERVER_URL": "http://host.docker.internal:8888",
        "TOKEN": "MY_TOKEN",
        "NOTEBOOK_PATH": "notebook.ipynb"
      }
    }
  }
}

Configuration for Linux

CLAUDE_CONFIG=${HOME}/.config/Claude/claude_desktop_config.json
cat <<EOF > $CLAUDE_CONFIG
{
  "mcpServers": {
    "jupyter-earth": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "SERVER_URL",
        "-e",
        "TOKEN",
        "-e",
        "NOTEBOOK_PATH",
        "--network=host",
        "datalayer/jupyter-earth-mcp-server:latest"
      ],
      "env": {
        "SERVER_URL": "http://localhost:8888",
        "TOKEN": "MY_TOKEN",
        "NOTEBOOK_PATH": "notebook.ipynb"
      }
    }
  }
}
EOF

✨ Features

Tools

1. download_earth_data_granules
   • Add a code cell in Jupyter Notebook to download data granules from NASA Earth Data.
   • Input:
     • folder_name (string): The name of the local folder to save the data.
     • short_name (string): The short name of the Earth dataset to download.
     • count (integer): The number of data granules to download.
     • temporal (tuple): (Optional) The time range, formatted as (date_from, date_to).
     • bounding_box (tuple): (Optional) The bounding box, formatted as (lower_left_lon, lower_left_lat, upper_right_lon, upper_right_lat).
   • Output: Cell output.

Prompts

1. download_analyze_global_sea_level
   • A prompt to request the download and analysis of global sea level data.
   • Output: A correctly formatted prompt.

🎥 Video Demonstration

🛠️ Build the Image

make build-docker

For more information, please refer to the project documentation or contact us.