The Model Context Protocol (MCP) server for NASA Earthdata Search enables AI assistants to access and search NASA's Common Metadata Repository (CMR) directly. With this integration, you can use natural language to query NASA's vast catalog of Earth science datasets through AI interfaces like Claude or ChatGPT.
Before installation, ensure you have:
Clone the repository to the same environment where your LLM client is running:
git clone https://github.com/podaac/cmr-mcp.git
cd cmr-mcp
UV is a Rust-based Python package manager required for this installation:
curl -LsSf https://astral.sh/uv/install.sh | sh
Set up a Python virtual environment:
uv venv
source .venv/bin/activate
Install all dependencies:
uv sync
To connect the MCP server with Claude Desktop:
Locate your Claude Desktop configuration file:
~/Library/Application Support/Claude/claude_desktop_config.json
Add the CMR MCP server configuration:
{
"mcpServers": {
"cmr": {
"command": "/path/to/your/uv",
"args": [
"--directory",
"/path/to/cmr-mcp/installation",
"run",
"cmr-search.py"
]
}
}
}
Replace the following:
/path/to/your/uv
: The output of which uv
command/path/to/cmr-mcp/installation
: Your current working directory where you cloned the repositoryOnce configured, you can use natural language queries to search NASA's dataset catalog. Simply start your prompts with "search cmr for..." followed by your search criteria.
The MCP server will translate your natural language request into appropriate CMR API calls and return relevant dataset information directly in your AI assistant's interface.
To add this MCP server to Claude Code, run this command in your terminal:
claude mcp add-json "cmr" '{"command":"$UV_LIB$","args":["--directory","$CMR_MCP_INSTALL$","run","cmr-search.py"]}'
See the official Claude Code MCP documentation for more details.
There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json
file so that it is available in all of your projects.
If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json
file.
To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".
When you click that button the ~/.cursor/mcp.json
file will be opened and you can add your server like this:
{
"mcpServers": {
"cmr": {
"command": "$UV_LIB$",
"args": [
"--directory",
"$CMR_MCP_INSTALL$",
"run",
"cmr-search.py"
]
}
}
}
To add an MCP server to a project you can create a new .cursor/mcp.json
file or add it to the existing one. This will look exactly the same as the global MCP server example above.
Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.
The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.
You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.
To add this MCP server to Claude Desktop:
1. Find your configuration file:
~/Library/Application Support/Claude/claude_desktop_config.json
%APPDATA%\Claude\claude_desktop_config.json
~/.config/Claude/claude_desktop_config.json
2. Add this to your configuration file:
{
"mcpServers": {
"cmr": {
"command": "$UV_LIB$",
"args": [
"--directory",
"$CMR_MCP_INSTALL$",
"run",
"cmr-search.py"
]
}
}
}
3. Restart Claude Desktop for the changes to take effect