home / mcp / google directory mcp server

Google Directory MCP Server

This read-only MCP Server allows you to connect to Google Directory data from Claude Desktop through CData JDBC Drivers. For full CRUD support, check out the first managed MCP platform: CData Connect AI (https://www.cdata.com/ai/).

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

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

You can query live Google Directory data through a lightweight MCP server that exposes Google Directory data via a simple MCP interface. This enables AI clients to read live information from Google Directory without writing SQL, making it ideal for answering natural language questions about contacts, groups, and directory items.

How to use

Use this MCP server with an MCP client to ask questions about Google Directory data. Once the server is running, the client can read data through built-in tools that retrieve table lists, column details, and run read-only queries. Typical usage patterns include asking questions like which groups a user belongs to, or how many users exist in a specific organizational unit. You don’t need to issue raw SQL queries; just ask your AI client to fetch the information you need.

The server operates in read-only mode locally, and you can connect to it from an MCP client on the same machine. For broader, remote access with full capabilities, explore the platform options that support MCP.”,

How to install

Prerequisites: Java runtime and Maven are needed to build and run the server.

# 1) Clone the project
git clone https://github.com/cdatasoftware/google-directory-mcp-server-by-cdata.git
cd google-directory-mcp-server-by-cdata

# 2) Build the server
mvn clean install

# This creates the JAR: CDataMCP-jar-with-dependencies.jar

Additional sections

License and usage notes: This server is provided under the MIT License. It is designed as a local, read-only MCP server to allow LLMs to query live data from Google Directory via the CData JDBC Driver.

Configuration steps (high level): You prepare a JDBC connection to Google Directory using the CData JDBC Driver, create a .prp file with connection properties, and then run the MCP server pointing to that .prp file. The article examples use a Salesforce-oriented PRP name, but you will adapt the path to your google-directory.prp as shown in the run command.

Running the MCP server locally: You start the server in stdio mode using a single command that launches the MCP runner with your PRP file. For example, the following command starts the server using a PRP file named Salesforce.prp (illustrative). You should replace it with your google-directory.prp when you run it.

java -jar /PATH/TO/CDataMCP-jar-with-dependencies.jar /PATH/TO/Salesforce.prp
```
Note: This configuration uses stdio, so the MCP client and server run on the same machine.

Troubleshooting

If you cannot see your MCP server in the client, ensure you have fully exited and restarted the client after starting the MCP server.

If data cannot be retrieved, verify that your .prp connection string is correct and that the JDBC driver is licensed and properly configured. Use the Connection String utility from the driver package to test connectivity and copy the resulting JDBC URL into your .prp file.

If you encounter issues with the MCP server itself, check the server logs for errors related to parsing the PRP, driver loading, or OAuth authentication flows, and consult the CData support resources for guidance.

Available tools

source_get_tables

Retrieves a list of tables available in the data source. The output is in CSV format with column headers on the first line.

source_get_columns

Retrieves a list of columns for a specified table. The output is in CSV format with column headers on the first line.

source_run_query

Executes a SQL SELECT query against the configured data source and returns the results.