広告掲載
MCP.so
ログイン

Earthdata MCP Server

@datalayer

リポジトリホームページ

基本情報

カテゴリ

その他

ライセンス

BSD-3-Clause

トランスポート

stdio

作者

datalayer

Earthdata MCP Server について

🌎 🔧 Earthdata MCP Server.

#ai#nasa#mcp#earth#spatial#nasa-api#earthdata#mcp-server

Earthdata MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

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

Earthdata MCP Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Earthdata MCP Server?

Earthdata MCP Server is a Model Context Protocol (MCP) server implementation that provides tools to interact with NASA Earth Data. It is intentionally Earthdata-only.

How to use Earthdata MCP Server?

Install the package via pip (pip install earthdata-mcp-server) or run it as a Docker container. Configure it in Claude Desktop by adding a mcpServers entry with the Docker command and environment variables EARTHDATA_USERNAME and EARTHDATA_PASSWORD. The server exposes three tools: search_earth_datasets, search_earth_datagranules, and download_earth_data_granules.

Key features of Earthdata MCP Server

  • Dataset discovery on NASA Earthdata
  • Granule search with temporal and bounding box filters
  • Flexible download workflow with explicit execution modes
  • Three‑tool interface for search, granule discovery, and download
  • Download modes: manifest, direct download, or Python script generation

Use cases of Earthdata MCP Server

  • Search NASA Earthdata for datasets matching a keyword
  • Query data granules filtered by time range and geographic bounding box
  • Download granules directly on the server side
  • Generate a Python script to execute downloads in a remote notebook or runtime
  • Compose with jupyter-mcp-server via mcp-compose for notebook‑driven analysis

よくある質問

1

What authentication is required?

NASA Earthdata Login credentials are required for the `download_earth_data_granules` tool. Set them via the environment variables `EARTHDATA_USERNAME` and `EARTHDATA_PASSWORD`.

2

Can I use this server with other MCP servers?

Yes, you can compose this server with `jupyter-mcp-server` using the `mcp-compose` tool. The README explicitly shows a recommendation for notebook‑driven execution via composition.

3

What download modes are available?

Three modes: `manifest` returns granule metadata without writing files; `download` saves files directly on the server runtime; `script` returns executable Python code for use in another runtime.

4

How do I run Earthdata MCP Server in Docker?

Add a JSON configuration block to your Claude Desktop settings with `"command": "docker"`, the appropriate arguments, and set the environment variables for your Earthdata credentials. Example configuration is provided in the README.

5

What runtime requirements does the server have?

Python 3.x via pip, or a Docker runtime. The server itself runs as a Python script (when installed locally) or inside a Docker container. No additional external services are required.

コメント

「その他」の他のコンテンツ

Blender

ahujasid

Open-source MCP to use Blender with any LLM

23.6K

Awesome Mlops

visenger

A curated list of references for MLOps

14.0K

Activepieces

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

23.2K

MaxKB

1Panel-dev

🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。

22.0K

Handl

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.

広告掲載