BigQuery (by LucasHild)
Free让 AI 检查 BigQuery 数据库模式并执行查询。
FreeFree tier
About BigQuery (by LucasHild)
A Model Context Protocol (MCP) server that provides LLMs with access to Google BigQuery. It enables AI assistants to inspect database schemas (list tables, describe table structure) and execute SQL queries using BigQuery dialect. The server supports flexible configuration via command-line arguments or environment variables, including project ID, location, dataset filtering, service account key file for authentication, and query timeout. It is open source under the MIT license and can be easily installed via Smithery, uvx, or manually integrated with Claude Desktop, Claude Code, and Cursor.
Key Features
Execute SQL queries using BigQuery dialect
List all tables in a BigQuery database
Describe the schema of a specific table
Configurable via command-line arguments or environment variables
Supports service account key file or default credentials
Option to filter specific datasets
Configurable query timeout
Open source with MIT license
Easily installable via Smithery, uvx, or manual MCP configuration
Pros & Cons
Pros
- Free and open source (MIT license)
- Easy setup with uvx or Smithery
- Flexible authentication (service account key or default credentials)
- Supports multiple datasets and timeout control
- Well-documented configuration and installation instructions
Cons
- Requires a Google Cloud Project and BigQuery API enabled
- Currently implements only three basic tools (execute-query, list-tables, describe-table)
- No built-in support for query streaming or cancellation
Best For
Allow AI assistants to explore and query BigQuery databasesAutomate data analysis by letting LLMs inspect schemas and run SQL queriesIntegrate BigQuery capabilities into Claude Desktop and Cursor via MCP
FAQ
What is the BigQuery MCP server?
It is an open-source Model Context Protocol server that allows LLMs to inspect Google BigQuery database schemas and execute SQL queries.
How do I install the BigQuery MCP server?
You can install it via Smithery using npx, or use uvx directly. It also supports manual configuration in Claude Desktop, Claude Code, and Cursor.
What tools does the server provide?
It provides three tools: execute-query (run a SQL query), list-tables (list all tables), and describe-table (describe a table's schema).
How do I configure authentication?
You can provide a service account key file using the --key-file option or set the BIGQUERY_KEY_FILE environment variable. If not provided, it uses default credentials.
Can I limit the server to specific datasets?
Yes, use the --dataset argument (repeatable) or BIGQUERY_DATASETS environment variable with comma-separated dataset names.