home / mcp / google data catalog mcp server

Google Data Catalog MCP Server

This read-only MCP Server allows you to connect to Google Data Catalog data from Claude Desktop through CData JDBC Drivers. For full CRUD support, check out our MCP Server for Google Data Catalog (https://www.cdata.com/drivers/googledatacatalog/download/mcp).

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "cdatasoftware-google-data-catalog-mcp-server-by-cdata": {
      "command": "java",
      "args": [
        "-jar",
        "CDataMCP-jar-with-dependencies.jar",
        "/PATH/TO/google-data-catalog.prp"
      ]
    }
  }
}

This MCP server provides a read-only interface to Google Data Catalog data through the CData JDBC Driver. It wraps the driver and exposes live Google Data Catalog information via a simple MCP protocol, enabling natural language queries from AI clients to retrieve up-to-date results without writing SQL.

How to use

You run a local MCP server that your AI client can talk to, using the standard MCP tools to read data from Google Data Catalog. The server operates in stdio mode, so it runs on the same machine as your client. Start the server with your prepared configuration file, then query tables, columns, or run simple SELECT statements through your MCP-enabled client. No SQL is required from the client side for common read operations.

How to install

Prerequisites you need before starting:

Install Java (JRE/JDK) for running the MCP server

Install Maven for building the MCP server package

Steps to set up and run the server exactly as shown here:

# 1. Build the MCP server package
mvn clean install

# This produces the JAR: CDataMCP-jar-with-dependencies.jar
```

```
# 2. Prepare the JDBC driver for Google Data Catalog and license it according to your OS
# (Follow the driver documentation to install and license the CData JDBC Driver for Google Data Catalog)
```

```
# 3. Create a .prp configuration file for your JDBC connection
# Example snippet shown in the guide
Prefix=googledatacatalog
ServerName=CDataGoogleDataCatalog
ServerVersion=1.0
DriverPath=PATH\\TO\\cdata.jdbc.googledatacatalog.jar
DriverClass=cdata.jdbc.googledatacatalog.GoogleDataCatalogDriver
JdbcUrl=jdbc:googledatacatalog:InitiateOAuth=GETANDREFRESH;
Tables=
```

```
# 4. Run the MCP server using the prepared .prp file
java -jar /PATH/TO/CDataMCP-jar-with-dependencies.jar /PATH/TO/google-data-catalog.prp

Additional configuration notes

The MCP server in this setup runs in stdio mode, suitable for local clients. Use the provided .prp file to point the server at your Google Data Catalog data source via the CData JDBC Driver.

If you are using Claude Desktop or another MCP client, you will also configure the client to start the server process and pass the path to the .prp file as shown in the client configuration examples.

Troubleshooting

If the MCP server does not appear in your client, ensure the server process is running and that the path to the .prp file is correct. Check that Java is installed and the JAR file exists at the specified path.

If you cannot test the connection to Google Data Catalog, verify that the JDBC driver is licensed and that the connection string in the .prp file is correct. If OAuth is required, complete the authentication flow as prompted by the driver utility.

Tools and usage patterns

This MCP server exposes read-only tools for querying Google Data Catalog data. You can use the built-in tools to list and inspect data structures and fetch data by running read-only queries through your MCP client.

License

This MCP server is released under the MIT License. You are free to use, modify, and distribute the software, in compliance with the terms of the MIT License.

All supported sources

The server supports Google Data Catalog through the CData JDBC Driver, enabling read access to its data models via MCP.

Available tools

googledatacatalog_mcp_get_tables

Retrieves a list of tables available in the Google Data Catalog data source. The output is returned in CSV format with a header row.

googledatacatalog_mcp_get_columns

Retrieves a list of columns for a specified table. The output is returned in CSV format with a header row.

googledatacatalog_mcp_run_query

Executes a SQL SELECT query against the Google Data Catalog data source and returns the result.