Claude Desktop connects to Google BigQuery through the CData Code Assist MCP for Google BigQuery using the Model Context Protocol (MCP).

When you launch Claude, it automatically detects MCP connections registered during setup. These connections are created and saved using the CData Code Assist MCP Configuration Tool, which is installed with the MCP server.

Each saved connection is recognized by Claude and can be referenced by name when asking questions.

Installing Claude

Claude Desktop は、Model Context Protocol（MCP）を使用して、サポートされているデータソースに対して自然言語クエリを実行できるスタンドアロンアプリケーションです。

MCP 経由でGoogle BigQuery に接続するには、はじめにClaude Desktop アプリケーションをインストールする必要があります。

最新バージョンは公式Claude ダウンロードページ からダウンロードできます。

Claude Desktop をインストールした後、CData MCP Driver for Google BigQuery を使用してMCP 接続を設定します。

How Claude Uses the Server

When you ask Claude a question, it launches the corresponding MCP server connection, reads the available tool descriptions provided by the connector, and generates a secure query in the background.

There is no need to write SQL or teach Claude how to query your data. Each tool is self-describing, and Claude consumes those descriptions to determine how to retrieve the right information.

Example Prompts

After setup, you can ask Claude natural-language questions like:

• "List all datasets I have access to in the 'my-project-id' project."
• "Which projects are available under my Google BigQuery account?"
• "Summarize how many tables exist in each dataset for the current project."
• "What partitioning information is available for the 'Sales' table?"
• "List all the external datasets in the current project."
• "What are the policy tags applied to columns in the 'Customers' table?"
• "Show all views defined in the 'Northwind' dataset."
• "Run the stored procedure 'MostPopularProduct' and display the result."
• "Which datasets contain partitioned tables?"
• "Get a list of tables and their descriptions in the 'Marketing' dataset."

Claude securely executes the query using the MCP server and responds using the live results from Google BigQuery.