What do I need before starting?
You need the Claude Desktop client, `uv` (installable via Homebrew), a Google Cloud project with datasets, and authenticated Application Default Credentials.
@MCP-Mirror
Basic information
Mirror of
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"Choose MCP Server": {
"command": "uvx",
"args": [
"choose-mcp-server"
],
"env": {
"PROJECT_ID": "",
"DATASETS": "",
"DBT_MANIFEST_FILEPATH": ""
}
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
Fetch the live tool list by running this server in a temporary sandbox using the button above.
Choose MCP Server Setup is a guide for configuring an MCP (Model Context Protocol) server that connects Claude Desktop to Google Cloud datasets and optionally a dbt manifest, enabling natural language queries against your data. It is for users who want to query cloud datasets through Claude Desktop.
Install uv via brew install uv, then edit claude_desktop_config.json (at ~/Library/Application\ Support/Claude) to add the server entry with uvx choose-mcp-server, your PROJECT_ID, comma-separated DATASETS, and optional DBT_MANIFEST_FILEPATH. Authenticate with gcloud auth login --update-adc, then open Claude Desktop to start asking questions.
claude_desktop_config.jsonYou need the Claude Desktop client, `uv` (installable via Homebrew), a Google Cloud project with datasets, and authenticated Application Default Credentials.
No, the `DBT_MANIFEST_FILEPATH` environment variable is optional.
Add the `APPDATA` environment variable to your server configuration, pointing to `C:\Users\YOUR_USERNAME\AppData\Roaming`.
Run `gcloud auth login --update-adc` to set your Application Default Credentials.
On macOS, it is at `~/Library/Application\ Support/Claude/claude_desktop_config.json`.

Connect your AI assistant to your own YOUB endurance training account. Read recorded activities with full analysis, planned sessions, race goals, wellness (HRV, sleep, resting HR) and your athletic profile. Create or mov

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.

Model Context Protocol Servers
YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context
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
Comments