home / mcp / google bigquery mcp server

Google BigQuery MCP Server

Provides a read-only MCP server to query live Google BigQuery data through a simple MCP interface.

Installation

Add the following to your MCP client configuration file.

Configuration

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

You can run a local, read-only MCP server that exposes Google BigQuery data to large language models. This server wraps the CData JDBC Driver and serves data through a simple MCP interface so you can ask natural-language questions and receive live results without writing SQL.

How to use

Once the MCP server is running, you connect your MCP client (for example Claude Desktop) to the local stdio server. You do not need to issue SQL queries yourself; instead, you ask the AI to retrieve information and it will call the available MCP tools under the hood. Typical use cases include querying table lists, inspecting column details, and running read-only queries against Google BigQuery data.

How to install

Prerequisites: you need a Java runtime environment (JDK 8 or newer) and Maven to build the 프로젝트. Ensure Java is available on your PATH by running java -version.

1) Build the MCP server jar.

mvn clean install
```
This creates the JAR file: CDataMCP-jar-with-dependencies.jar

2) Prepare a JDBC connection file for Google BigQuery. Create a file named google-bigquery.prp with these properties (adjust paths to your environment):

Prefix=googlebigquery
ServerName=CDataGoogleBigQuery
ServerVersion=1.0
DriverPath=PATH\TO\cdata.jdbc.googlebigquery.jar
DriverClass=cdata.jdbc.googlebigquery.GoogleBigQueryDriver
JdbcUrl=jdbc:googlebigquery:InitiateOAuth=GETANDREFRESH;
Tables=

Use with Claude Desktop or another MCP client

Create a config entry for the MCP server in your client. The server runs locally and is started via a standard Java invocation that points to your built jar and the .prp file.

java -jar /PATH/TO/CDataMCP-jar-with-dependencies.jar /PATH/TO/google-bigquery.prp

Available tools

google_bigquery_get_tables

Retrieves a list of tables available in the data source. Output is in CSV format with headers in the first line.

google_bigquery_get_columns

Retrieves a list of columns for a specified table. Output is in CSV format with headers in the first line.

google_bigquery_run_query

Executes a SQL-like SELECT query against the exposed data source and returns the results.