google-bigquery-mcp-server-by-cdata
@CDataSoftware
This read-only MCP Server allows you to connect to Google BigQuery data from Claude Desktop through CData JDBC Drivers. Free (beta) read/write servers available at
Overview
What is google-bigquery-mcp-server-by-cdata?
google-bigquery-mcp-server-by-cdata is a read-only MCP server that lets LLMs (such as Claude Desktop) query live Google BigQuery data using natural language. It wraps CData’s JDBC Driver for Google BigQuery, exposing the data as relational SQL models without requiring direct SQL from the user.
How to use google-bigquery-mcp-server-by-cdata?
Clone the repository, build with mvn clean install, download and license the CData JDBC Driver for Google BigQuery, create a .prp file with your JDBC connection string and table settings, then add the server to Claude Desktop’s claude_desktop_config.json. The server runs on stdio and must be on the same machine as the client.
Key features of google-bigquery-mcp-server-by-cdata
- Read-only MCP server for Google BigQuery
- Natural language querying via LLMs
- Exposes tables and columns through built‑in tools
- Uses the CData JDBC Driver for Google BigQuery
- Requires Java and a configured
.prpfile - Communicates over
stdiotransport
Use cases of google-bigquery-mcp-server-by-cdata
- Let LLMs answer questions about live BigQuery data without writing SQL
- Retrieve metadata (tables, columns) from a BigQuery dataset
- Integrate BigQuery queries into conversational AI assistants like Claude Desktop
- Explore BigQuery data interactively with natural language prompts
FAQ from google-bigquery-mcp-server-by-cdata
Is this server read‑only, or can it write/update/delete data?
This server is explicitly read‑only. For full CRUD capabilities, CData offers a separate free beta MCP Server for Google BigQuery.
What are the runtime dependencies?
You need Java, Maven (to build), and the CData JDBC Driver for Google BigQuery (downloaded and licensed separately). A .prp configuration file is also required.
How does the server connect to my data?
The server uses a JDBC connection string configured in the .prp file. It connects live to Google BigQuery through the CData JDBC Driver, which handles OAuth and other authentication.
What transport does the server use?
The server uses stdio transport, so it must run on the same machine as the MCP client (e.g., Claude Desktop).
Which tools does the server expose?
It exposes three tools: {servername}_get_tables, {servername}_get_columns, and {servername}_run_query (for SELECT queries).