Google Cloud Storage MCP Server by CData

@CDataSoftware

代码仓库

基本信息

分类

文件与存储

传输方式

stdio

作者

CDataSoftware

提交者

Cameron Leblanc

关于 Google Cloud Storage MCP Server by CData

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 Cloud Storage (beta): https://www.cdata.com/download/download.aspx?sku=HPZK-V&type=beta

#google-cloud-storage#mcp-server #cdata

Google Cloud Storage MCP Server by CData 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "{classname_dash}": {
      "command": "PATH\\TO\\java.exe",
      "args": [
        "-jar",
        "PATH\\TO\\CDataMCP-jar-with-dependencies.jar",
        "PATH\\TO\\google-cloud-storage.prp"
      ]
    }
  }
}

Google Cloud Storage MCP Server by CData 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is Google Cloud Storage MCP Server by CData?

Google Cloud Storage MCP Server by CData is a read-only Model Context Protocol server that allows LLMs (such as Claude Desktop) to query live data from Google Cloud Storage using natural language. It is built on the CData JDBC Driver for Google Cloud Storage, which exposes the storage as relational SQL models.

How to use Google Cloud Storage MCP Server by CData?

Clone the repository, build with mvn clean install, download and license the CData JDBC Driver for Google Cloud Storage, configure a connection string using the driver’s utility, create a .prp file with required properties (Prefix, ServerName, DriverPath, DriverClass, JdbcUrl, etc.), and add an entry to the client’s MCP configuration (e.g., claude_desktop_config.json) pointing to java -jar CDataMCP-jar-with-dependencies.jar <prp-file>. The server uses stdio transport, so it must run on the same machine as the client.

Key features of Google Cloud Storage MCP Server by CData

Read-only access to Google Cloud Storage data
Exposes data as relational SQL models
Three built-in MCP tools: get_tables, get_columns, run_query
Natural language interface through compatible LLM clients
Standard MCP configuration for easy setup

Use cases of Google Cloud Storage MCP Server by CData

Querying cloud storage metadata with natural language
Analyzing stored data without writing SQL
Integrating Google Cloud Storage data into AI workflows
Retrieving live storage information for decision support

常见问题

Is this server read-only?

Yes. This server provides read-only access. For full CRUD capabilities, see the separate CData MCP Server for Google Cloud Storage (beta).

What are the runtime requirements?

Java, Maven (for building), and the CData JDBC Driver for Google Cloud Storage (requires a trial or licensed key).

How is data accessed?

The server communicates over `stdio` transport, so the client and server must run on the same machine.

What tools does the server expose?

Three tools: `{prefix}_get_tables` lists available tables, `{prefix}_get_columns` lists columns of a table, and `{prefix}_run_query` executes a SQL SELECT query. Results are returned in CSV format.