Snow Leopard BigQuery

Bridges AI agents to BigQuery datasets via MCP, enabling natural language queries and schema exploration.

python

10

GitHub Stars

python

Language

2 months ago

First Indexed

3 weeks 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": {
    "snowleopard-ai-bigquery-mcp": {
      "command": "uvx",
      "args": [
        "sl-bigquery-mcp",
        "--dataset",
        "bigquery-public-data.usa_names",
        "--project",
        "🚨 <projectName> 🚨"
      ],
      "env": {
        "BQ_PROJECT": "<projectName>"
      }
    }
  }
}

You can connect an AI agent to Google BigQuery through natural language queries and schema exploration by using the Snow Leopard BigQuery MCP Server. This MCP server acts as a bridge between AI agents and your BigQuery datasets, enabling seamless data querying and schema discovery in a secure, standardized way.

How to use

To use the BigQuery MCP server, you configure an MCP client to communicate with the local or remote MCP endpoint. You will leverage the available resources to list tables and fetch schemas, then run SQL queries against BigQuery and receive results in a structured format. The server exposes practical actions for interacting with your datasets without exposing raw credentials in your prompts.

How to install

Prerequisites you need before installing:
- Python installed on your system
- Access to a Google Cloud Project with BigQuery enabled
- uvx installed to run MCP servers
- An MCP client capable of speaking the MCP protocol (for example, an AI agent that supports MCP)

# Install the MCP client runtime if required (example placeholder since exact steps depend on your setup)
# This section uses uvx as shown in the configuration example

# Ensure you have uvx available on your system. If needed, install or locate the uvx executable.

Runtime configuration and starting the server

The following configuration shows how to register the BigQuery MCP server with your MCP client setup. This config mounts the server as a local process that your client can talk to via standard input/output.

{
  "mcpServers": {
    "bigquery": {
      "command": "uvx",
      "args": [
        "sl-bigquery-mcp", 
        "--dataset",
        "bigquery-public-data.usa_names",
        "--project",
        "🚨 <projectName> 🚨"
      ]
    }
  }
}

Available tools

list_tables

List all tables available to the agent within the configured dataset.

get_schema

Retrieve the schema of a specified table to understand its columns and types.

query

Execute a BigQuery SQL query and return the results to the agent.