CMR
- python
4
GitHub Stars
python
Language
6 months ago
First Indexed
2 months ago
Catalog Refreshed
Documentation & install
Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.
Installation
Add the following to your MCP client configuration file.
Configuration
View docs{
"mcpServers": {
"podaac-cmr-mcp": {
"command": "$UV_LIB$",
"args": [
"--directory",
"$CMR_MCP_INSTALL$",
"run",
"cmr-search.py"
]
}
}
}You set up an MCP server that lets you query NASA Earthdata CMR datasets through AI-powered retrieval. This server runs locally via a lightweight interface and integrates with your AI agent to perform fast, targeted searches of the CMR catalog.
How to use
Start your MCP server once you have the runtime tool installed. The server exposes a command-driven entry point you invoke from your AI client. To search for datasets, prompt your agent with phrases like search cmr for.... You can tailor queries by date ranges, data providers, and keywords. Useful example prompts include: 1) Search CMR for datasets from 2024 to 2025 2) Search CMR for PO.DAAC datasets from 2020 to 2024 with keyword Climate.
How to install
Prerequisites you need before starting include a Python-compatible environment and a runtime command line tool for MCP execution. Follow these steps in order to prepare your system.
# 1) Install the runtime manager for MCP execution
# 2) Prepare a virtual environment (if desired) and activate it
# 3) Install MCP dependencies via the runtime manager
# 4) Run the MCP server configuration as described below
Additional notes
Configuration for integrating with your AI client is provided as a ready-to-use example. The standard setup uses a stdio-based command where the MCP runner is invoked through the runtime tool and points to a Python script that performs the CMR search.
Available tools
cmr_search
Executes the CMR search workflow by running the cmr-search.py script to retrieve dataset metadata from NASA Earthdata CMR.