Earthdata MCP Server

If you need notebook/runtime tools, compose this server with `jupyter-mcp-server` using [mcp-compose](https://github.com/datalayer/mcp-compose).

Local serverstdioPython

What is the Earthdata MCP server?

Connect Earthdata to Claude, Cursor or any other MCP client and it stops being a tab you switch to. If you need notebook/runtime tools, compose this server with jupyter-mcp-server using mcp-compose. The earthdata mcp server is what makes that connection.

What the server does

  • Dataset discovery on NASA Earthdata
  • Granule search with temporal and bounding box filters
  • Flexible download workflow with explicit execution modes

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

  • search_earth_datasets — The search_earth_datasets tool exposed by this server
  • search_earth_datagranules — The search_earth_datagranules tool exposed by this server
  • download_earth_data_granules — The download_earth_data_granules tool exposed by this server

Installation

Installation goes through your MCP client rather than a global install: point it at earthdata-mcp-server on PyPI and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

Credentials and setup notes

Configuration is passed through the environment: EARTHDATA_USERNAME, EARTHDATA_PASSWORD. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Where it fits

This sits in the developer tooling group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Earthdata's toolset — search_earth_datasets, search_earth_datagranules, download_earth_data_granules — is a fair guide to whether it matches your workflow. It is maintained by datalayer; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Earthdata's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Worth knowing first

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
search_earth_datasetsThe search_earth_datasets tool exposed by this server.
search_earth_datagranulesThe search_earth_datagranules tool exposed by this server.
download_earth_data_granulesThe download_earth_data_granules tool exposed by this server.

How to install the Earthdata MCP server

### Docker with Claude Desktop

```json
{
  "mcpServers": {
    "earthdata": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "datalayer/earthdata-mcp-server:latest"
      ],
      "env": {
        "EARTHDATA_USERNAME": "your_username",
        "EARTHDATA_PASSWORD": "your_password"
      }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
EARTHDATA_USERNAMEConfiguration value read at startup.Optional
EARTHDATA_PASSWORDConfiguration value read at startup.Optional

Example prompts to try

  • Use Earthdata to search earth datasets.
  • Use Earthdata to search earth datagranules.
  • Use Earthdata to download earth data granules.

Frequently asked questions

It connects Earthdata to MCP-compatible AI assistants such as Claude and Cursor, exposing 3 tools (search_earth_datasets, search_earth_datagranules, download_earth_data_granules) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Earthdata directly.