Connect BigQuery to Claude
Give your team's AI tools governed, real-time access to BigQuery. Engineering and security teams deploy once through Mint and every Claude user gets secure, audited access without sharing credentials or writing custom integrations.
What are the top 10 customers by revenue this quarter from our BigQuery database?
I'll query your BigQuery database for this quarter's revenue data:
- Querying BigQuery for quarterly revenue by customer...
- Found 847 customers — top 10 account for 62% of revenue
- Acme Corp leads at $2.4M, up 18% from last quarter
All actions logged and governed
How it works
Provide your BigQuery connection details. We'll securely connect to your data source.
Configure the tools and data available to your AI agents.
We convert your config into a production-ready MCP server with enterprise governance.
Select your preferred AI client
One-time setup connects BigQuery to all your AI tools
How to connect
Connect your BigQuery database
- GCP project ID: Your Google Cloud project containing BigQuery datasets
- Query location: Optional region specification for query job execution
- Write mode configuration: Control write permissions: allowed, blocked, or protected
- Dataset access restrictions: Optionally limit tool access to specific datasets across projects
- Automatic deployment: We deploy your MCP server with enterprise governance—no manual setup required
Link your BigQuery MCP to Claude
- Open Claude Settings → Connectors
- Click "Add custom connector" and enter your Mintive Gateway URL
- Authenticate with Mintive Gateway via OAuth
- Enable the connector in any conversation via the + button → Connectors
- Start querying your BigQuery data directly in Claude
What you get
Faster deployment
Rapid iteration
Enterprise governance
Why Mintive gateway
Centralized governance
One-click deployment
OAuth + SSO enforcement
Host stdio servers on Mint instead of running locally
Observability and control
Enterprise hardening
Supports shared and per-user auth
Granular tool access control
Use cases
Conversational analytics on petabyte-scale data
Enable teams to query billions of events and user interactions through natural language—AI agents analyze engagement patterns, content performance, and user behavior without writing SQL on massive datasets.
Fraud detection with cross-source analysis
Let AI agents investigate suspicious transactions by joining financial data with external feeds and unstructured sources through natural language—detecting fraud patterns across petabyte-scale data without manual queries.
Marketing analytics and attribution
Enable marketing teams to analyze campaign performance, customer segments, and attribution paths by asking questions in natural language—AI agents query BigQuery's marketing data warehouse without SQL expertise.
Select your database
Connect to 30+ database types including SQL, NoSQL, and cloud-native databases
FAQs
Yes. While this page focuses on Claude, Mint works with ChatGPT, Claude, Claude Code, VS Code, Cursor, and any MCP-compatible client.