mcp-bigquery-server
BigQuery MCP Server enables seamless and secure interaction between AI models like Claude and BigQuery databases using natural language. It features natural language query capabilities, secure data handling, and easy setup options.
What is the Model Context Protocol (MCP)?
MCP is a protocol designed to facilitate communication between AI models and databases, acting as a universal translator for AI-database interactions.
What are the prerequisites for using BigQuery MCP Server?
You need Node.js 14 or higher, a Google Cloud project with BigQuery enabled, and either Google Cloud CLI or a service account key file. Claude Desktop is also required as the LLM interface.
How do I authenticate with Google Cloud for BigQuery MCP Server?
You can authenticate using Google Cloud CLI for development or a service account key file for production environments.
What permissions are needed to use BigQuery MCP Server?
You need either the 'roles/bigquery.user' role or both 'roles/bigquery.dataViewer' and 'roles/bigquery.jobUser' roles.
What are the current limitations of BigQuery MCP Server?
MCP support is only available in Claude Desktop, connections are limited to local MCP servers, queries are read-only with a 1GB limit, and some complex view types may have limitations.