CMR FAQs

Question 1

How do I prompt my agent to use CMR?

Accepted Answer

Simply prompt your agent to 'search cmr for...' data. For example, 'Search CMR for datasets from 2024 to 2025' or 'Search CMR for PO.DAAC datasets from 2020 to 2024 with keyword Climate'.

Question 2

How does CMR work with AI models?

Accepted Answer

CMR acts as an MCP server, allowing LLM clients like Claude and ChatGPT to query NASA Earthdata Search using natural language. It translates these queries into dataset searches.

Question 3

What is CMR?

Accepted Answer

CMR is a tool that uses the Model Context Protocol (MCP) to integrate AI retrievals with NASA's Earthdata Search, making it easier to find datasets using natural language.

Question 4

What are the benefits of using CMR?

Accepted Answer

CMR simplifies NASA Earthdata Search by enabling natural language queries. This eliminates the need to understand complex search parameters, making data discovery more accessible. It allows users to find NASA datasets using AI models.

Question 5

What do I need to install to use CMR?

Accepted Answer

You'll need a LLM client such as Claude or ChatGPT, and `uv`, a rust-based python package manager. Follow the installation steps in the CMR's GitHub repository to set up the MCP server.

CMR

Key Features

Use Cases

CMR

Key Features

Use Cases