:heavy_exclamation_mark: This project builds a local, read-only MCP server. For fully remote MCP access, check out the first managed MCP platform
If you want an AI assistant working directly with Google Directory By Cdata, the google directory by cdata mcp server is the bridge. :heavy_exclamation_mark: This project builds a local, read-only MCP server. For fully remote MCP access, check out the first managed MCP platform: CData Connect AI. For locally hosted, full read, write, update, delete, and action capabilities and a simplified setup.
:heavy_exclamation_mark: This project builds a local, read-only MCP server. For fully remote MCP access, check out the first managed MCP platform: CData Connect AI. For locally hosted, full read, write, update, delete, and action capabilities and a simplified setup, check out our CData MCP Server for Google Directory. ## Purpose We created this read-only MCP Server to allow LLMs (like Claude Desktop) to query live data Google Directory supported by the CData JDBC Driver for Google Directory.
Once connected, the assistant can call these 3 tools directly:
source_get_tables — The source_get_tables tool exposed by this serversource_get_columns — The source_get_columns tool exposed by this serversource_run_query — The source_run_query tool exposed by this serverSetup follows the standard MCP pattern: clone or install the server, then register it in your client's configuration file and restart the client. The configuration snippets on this page cover Claude Desktop, Claude Code and Cursor.
File and storage servers are what separate an assistant that talks about your documents from one that actually works with them. Google Directory By Cdata sits in that group, and the shape of its toolset — source_get_tables, source_get_columns, source_run_query — tells you what it is really for. Worth comparing against the other file systems servers in this directory before you commit to one, since several overlap in scope but differ sharply in setup cost and permissions.
| Tool | What it does |
|---|---|
| source_get_tables | The source_get_tables tool exposed by this server. |
| source_get_columns | The source_get_columns tool exposed by this server. |
| source_run_query | The source_run_query tool exposed by this server. |
**Linux/Mac**
```json
{
"mcpServers": {
"{classname_dash}": {
"command": "/PATH/TO/java",
"args": [
"-jar",
"/PATH/TO/CDataMCP-jar-with-dependencies.jar",
"/PATH/TO/google-directory.prp"
]
},
...
}
}Configuration as documented by the project. Restart the client after saving.
Your workspace, on speaking terms with AI — search, read and write Notion pages and databases.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Search and read your Drive — Docs, Sheets and files become context your assistant can actually use.
Your assistant inside the workspace — read channels, search history, post messages and tame the noise.
Metabase ships its own MCP endpoint — search your BI content, build and run queries, and save questions and dashboards without leaving the chat.
Stop letting your assistant hallucinate n8n node parameters — this server hands it the real schemas, templates and validation.