Azure Data Lake Storage MCP Server by CData

Name: Azure Data Lake Storage MCP Server by CData
Author: CDataSoftware

@CDataSoftware

About Azure Data Lake 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 Azure Data Lake Storage (beta): https://www.cdata.com/download/download.aspx?sku=HDZK-V&type=beta

#azure #data-lake #mcp-server #cdata

Basic information

Config

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\\azure-data-lake-storage.prp"
      ]
    }
  }
}

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Azure Data Lake Storage MCP Server by CData?

A read-only MCP server that lets LLMs like Claude Desktop query live Azure Data Lake Storage data using natural language. It wraps the CData JDBC Driver for Azure Data Lake Storage, which exposes the storage as relational SQL models.

How to use Azure Data Lake Storage MCP Server by CData?

Clone the repo, build with mvn clean install, download and license the CData JDBC Driver for Azure Data Lake Storage, configure a connection string, create a .prp file with connection details, and add the server to Claude Desktop’s claude_desktop_config.json. Run with java -jar CDataMCP-jar-with-dependencies.jar <path-to>.prp. The server uses stdio transport and must run on the same machine as the client.

Key features of Azure Data Lake Storage MCP Server by CData

Read-only access to Azure Data Lake Storage data
Exposes data as SQL tables via CData JDBC Driver
Tools: get_tables, get_columns, run_query (SELECT only)
Natural language querying — no SQL required from the user
Open source under MIT License

Use cases of Azure Data Lake Storage MCP Server by CData

Ask an LLM questions about stored data without writing SQL
Explore table schemas and column definitions interactively
Retrieve live data from Azure Data Lake Storage for AI-driven analysis
Quickly prototype data insights using conversational AI

FAQ from Azure Data Lake Storage MCP Server by CData

Is this server read-only?

Yes, the server explicitly states it is read-only. For full create, read, update, delete and action capabilities, use the free CData MCP Server for Azure Data Lake Storage (beta) linked in the README.

What runtime dependencies are required?

Java and the CData JDBC Driver for Azure Data Lake Storage must be installed and licensed. The driver JAR file path is specified in the .prp configuration.

What transport protocol does the server use?

It uses stdio transport, so the server must be run on the same machine as the MCP client (e.g., Claude Desktop).

Can I perform write or update operations?

No, this server only supports SELECT queries via the run_query tool. No INSERT, UPDATE, DELETE, or custom actions are available.

How do I authenticate to Azure Data Lake Storage?

The README instructs you to use the CData JDBC Driver’s connection string utility. If the data source uses OAuth, you will authenticate in your browser during the connection test.