Is this server read-only or can it write data?
The README explicitly states this project builds a read-only MCP server. For full create, update, delete, and action capabilities, CData offers a separate free beta server.
@CDataSoftware
Basic information
This project builds a read-only MCP server. For full read, write, update, delete, and action capabilities and a simplified setup, check out our free CData MCP Server for Google Directory (beta): https://www.cdata.com/download/download.aspx?sku=EUZK-V&type=beta
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"{classname_dash}": {
"command": "PATH\\TO\\java.exe",
"args": [
"-jar",
"PATH\\TO\\CDataMCP-jar-with-dependencies.jar",
"PATH\\TO\\google-directory.prp"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Google Directory MCP Server by CData is a read-only Model Context Protocol (MCP) server that enables LLMs like Claude Desktop to query live data from Google Directory using natural language. It wraps the CData JDBC Driver for Google Directory, which exposes Google Directory as relational SQL models, and makes that data available through a simple MCP interface—no SQL required.
Clone the repository, build the JAR with mvn clean install, install and license the CData JDBC Driver for Google Directory, then configure a .prp file with your connection details. Add the server to your Claude Desktop config (claude_desktop_config.json) using the Java command that points to the JAR and the .prp file. Run or refresh your client to start querying.
get_tables, get_columns, run_querystdio transport (client and server on same machine)The README explicitly states this project builds a read-only MCP server. For full create, update, delete, and action capabilities, CData offers a separate free beta server.
You need Java installed, the CData JDBC Driver for Google Directory (downloaded and licensed), and the server must run on the same machine as the client because it uses `stdio` transport.
Configure a `.prp` file with the JDBC connection string (e.g., `jdbc:googledirectory:InitiateOAuth=GETANDREFRESH;`), and set the path to the driver JAR and driver class (`cdata.jdbc.googledirectory.GoogleDirectoryDriver`).
It provides `{servername}_get_tables` (list tables), `{servername}_get_columns` (list columns for a table), and `{servername}_run_query` (execute a SQL SELECT query). All output is CSV.
The server queries Google Directory live via the JDBC driver; no data is stored by the server. The driver handles authentication and data retrieval directly from Google.

Model Context Protocol Servers
📄 The PDF intelligence layer for AI agents — Agent Document Twin, evidence-first extraction, visual crops, OCR provenance, trust reports, and benchmark-gated releases. MCP server for Claude, Cursor, VS Code, and any MCP client.
A lightweight MCP server for processing, editing, and interacting with PDF, Word, Excel, and CSV documents.
MCP server to integrate AWS S3 and LLM
MCP server for working with PDF files
Comments