Google Data Catalog MCP Server by CData

What is Google Data Catalog MCP Server by CData?

A read-only Model Context Protocol (MCP) server that enables large language models (LLMs) to query live data from Google Data Catalog. It is built on the CData JDBC Driver for Google Data Catalog, which exposes the data source as relational SQL models. The server wraps that driver in an MCP interface, allowing LLMs to retrieve information using natural language without writing SQL.

How to use Google Data Catalog MCP Server by CData?

Build the server with Maven (mvn clean install), download and install the CData JDBC Driver for Google Data Catalog, license the driver, and create a .prp configuration file with your JDBC connection string. Then add the server to your Claude Desktop configuration (claude_desktop_config.json) pointing to the built JAR and the .prp file. Run or refresh Claude Desktop to use the tools.

Key features of Google Data Catalog MCP Server by CData

• Read-only MCP server for querying Google Data Catalog
• Powered by CData JDBC Driver for Google Data Catalog
• Exposes tables and columns as tools (get_tables, get_columns, run_query)
• Communicates via stdio transport (client must be on same machine)
• Supports all tables by default or can restrict to specific tables
• Works with any MCP client like Claude Desktop

Use cases of Google Data Catalog MCP Server by CData

• Ask natural‑language questions about your data catalog assets (“What tables are in my catalog?”)
• Retrieve metadata such as table schemas and column details
• Execute SQL SELECT queries against live Google Data Catalog data
• Enable LLM‑driven data discovery and governance workflows

FAQ from Google Data Catalog MCP Server by CData

Is this server read‑only?

Yes. The README explicitly states it is a read‑only MCP server. For full read, write, update, and delete capabilities, use the separate CData MCP Server for Google Data Catalog (beta) available on the CData website.

What runtime and dependencies are required?

You need Java to run the JAR file and Maven to build the project. Additionally, the CData JDBC Driver for Google Data Catalog must be downloaded, installed, and licensed separately.

How is the connection configured?

Connections are defined in a .prp file that includes the JDBC URL, driver path, driver class, and optionally a list of tables to expose. The JDBC connection string can be generated using the driver’s connection string utility, which supports OAuth-based authentication.

Where does the data reside?

The data stays in your Google Data Catalog instance. The server never stores or copies the data; it queries it live through the JDBC driver.

What transport does the server use?

It uses stdio transport, so the MCP client must run on the same machine as the server. This means remote clients cannot connect directly to this server.