广告合作
MCP.so
登录
A

Azure Data Catalog MCP Server by CData

@CDataSoftware

代码仓库

基本信息

分类

数据与分析

传输方式

stdio

作者

CDataSoftware

提交者

Cameron Leblanc

关于 Azure Data Catalog 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 Azure Data Catalog (beta): https://www.cdata.com/download/download.aspx?sku=GNZK-V&type=beta

#azure#data-catalog#mcp-server

Azure Data Catalog 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\\azure-data-catalog.prp"
      ]
    }
  }
}

Azure Data Catalog 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 Azure Data Catalog MCP Server by CData?

A read-only MCP server that allows LLMs like Claude Desktop to query live Azure Data Catalog data via natural language. It wraps the CData JDBC Driver for Azure Data Catalog, exposing the catalog as relational SQL models through a simple MCP interface.

How to use Azure Data Catalog MCP Server by CData?

Clone the repository, build with mvn clean install, install and license the CData JDBC Driver for Azure Data Catalog, create a .prp file with connection details, then add the server to claude_desktop_config.json. The server uses stdio transport and runs locally alongside the AI client.

Key features of Azure Data Catalog MCP Server by CData

  • Read-only access to Azure Data Catalog via MCP
  • Uses the CData JDBC Driver for Azure Data Catalog
  • Allows natural language queries – no SQL required
  • Provides tools: get_tables, get_columns, run_query (SELECT only)
  • Works with Claude Desktop and other MCP clients
  • Outputs results in CSV format

Use cases of Azure Data Catalog MCP Server by CData

  • Ask an LLM to list all data assets in Azure Data Catalog.
  • Retrieve metadata about specific tables or columns without writing SQL.
  • Explore the structure of your Azure Data Catalog using natural language questions.
  • Integrate live catalog metadata into AI-driven data discovery workflows.

常见问题

1

Is this server read-only?

Yes, it is explicitly a read-only MCP server. It only supports SQL SELECT queries via the `run_query` tool.

2

What dependencies are required?

Java, Maven, and the CData JDBC Driver for Azure Data Catalog (which must be licensed – a trial key is available).

3

What transport does the server use?

The server uses stdio transport and can only be used with clients running on the same machine.

4

How do I authenticate to Azure Data Catalog?

Authentication is configured in the JDBC connection string (e.g., OAuth). Use the CData Connection String utility to set it up and test the connection before creating the `.prp` file.

5

Is there a full read-write version?

Yes, CData offers a free beta MCP Server for Azure Data Catalog that supports full CRUD and actions, with simplified setup.

评论

数据与分析 分类下的更多 MCP 服务器

HousingFeed

HousingFeed

US rental listings for AI assistants: free live search and rent statistics, plus licensed feeds.

Forency

cheevahagadog

Investigate any website's technology stack: CMS, eCommerce, frameworks, analytics, CRM, payments, and hosting behind any URL. Ask "which of these 15 prospects use HubSpot vs Salesforce?" and get a table back. Free tier:

1

SocialAPIs — Facebook & Instagram Data

SocialAPIsHub

Facebook & Instagram data for AI agents — pages, posts, groups, Ads Library, Marketplace, profiles and reels. 47 read-only tools with structured output.

1

LeadBoxer

Company and contact enrichment: identify the company behind an IP, get firmographics for a domain, and profile a work email.

AudD Music Recognition

AudD

AudD MCP is a way for agents to add music recognition to apps or to fulfill song identification requests. It connects you to AudD, the music recognition API.

广告合作