Integrates with dbt through a manifest file path, likely enabling querying or analysis of dbt models and metadata.
Authenticates with Google Cloud using Application Default Credentials, with access to datasets based on a Project ID.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Choose MCP Servershow me the top 10 products by sales from the ecommerce dataset"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Choose MCP Server Setup
Start by downloading the Claude Desktop Client: https://claude.ai/download
Install uv
brew install uvInstall the MCP server
Edit the claude_desktop_config.json file (located in ~/Library/Application\ Support/Claude) and add the following to the mcpServers section:
{
"mcpServers": {
"Choose MCP Server": {
"command": "uvx",
"args": ["choose-mcp-server"],
"env": {
"PROJECT_ID": YOUR_PROJECT_ID,
"DATASETS": DATASET_1,DATASET_2,DATASET_3
"DBT_MANIFEST_FILEPATH": YOUR_DBT_MANIFEST_FILEPATH
}
}
}
}N.B: the dbt manifest file path is optional.
Log into Google Cloud and update your Application Default Credentials (ADC)
gcloud auth login --update-adcOpen Claude Desktop and start asking questions!
Troubleshooting
For Windows users, you may need to add the APPDATA environment variable to your Claude Desktop config file.
"env": {
"APPDATA": "C:\\Users\\YOUR_USERNAME\\AppData\\Roaming",
}This server cannot be installed
Resources
Looking for Admin?
Admins can modify the Dockerfile, update the server description, and track usage metrics. If you are the server author, to access the admin panel.