home / mcp / azure data catalog mcp server

Azure Data Catalog MCP Server

This read-only MCP Server allows you to connect to Azure Data Catalog data from Claude Desktop through CData JDBC Drivers. For full CRUD support, check out our MCP Server for Azure Data Catalog (https://www.cdata.com/drivers/azuredatacatalog/download/mcp).

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "cdatasoftware-azure-data-catalog-mcp-server-by-cdata": {
      "command": "java",
      "args": [
        "-jar",
        "/PATH/TO/CDataMCP-jar-with-dependencies.jar",
        "/PATH/TO/azure-data-catalog.prp"
      ]
    }
  }
}

This read-only MCP server lets you query live Azure Data Catalog data via the CData JDBC Driver without writing SQL. It exposes data through a simple MCP interface so you can ask natural language questions and receive results in real time.

How to use

You connect an MCP client or AI assistant to the server and start queries using the built-in tools. Ask questions like “What are my open opportunities grouped by account industry?” or “Show the list of tables and their row counts.” The server translates your requests into read-only data operations against Azure Data Catalog and returns structured results. No SQL is required on your end.

How to install

Prerequisites you must have installed on your machine before starting:

Java Runtime Environment (JRE) 1.8+ or higher
Maven (for building the MCP server)
Access to the CData JDBC Driver for Azure Data Catalog (license if required)

Step 1: Clone the MCP server repository and navigate into it.

git clone https://github.com/cdatasoftware/azure-data-catalog-mcp-server-by-cdata.git
cd azure-data-catalog-mcp-server-by-cdata

Step 2: Build the MCP server to produce the JAR used at runtime.

mvn clean install

Step 3: Download and license the CData JDBC Driver for Azure Data Catalog from CData. Follow the installer prompts and then license the driver.

Step 4: Configure the JDBC connection and save the property file (azure-data-catalog.prp) with your connection details. You will run a Connection String utility to test and copy the resulting JDBC URL.

Step 5: Create the MCP configuration file for your JDBC connection (azure-data-catalog.prp) using the provided properties and format.

Step 6: Start the MCP server using the final run command detailed below.

Running the MCP server on your machine

To run the MCP server, execute the following command with your actual paths. This starts the server in stdio mode, which means the server runs on the same machine as the client.

java -jar /PATH/TO/CDataMCP-jar-with-dependencies.jar /PATH/TO/azure-data-catalog.prp

Post-setup usage

After the server starts, your MCP client (for example an AI assistant) can discover and invoke the following tools against Azure Data Catalog. You don’t need to call them directly; simply ask questions and the client will use these tools under the hood.

Available tools

azuredatacatalog_get_tables

Retrieves a list of available tables in the data source. The output is CSV with a header row describing columns.

azuredatacatalog_get_columns

Retrieves a list of columns for a specified table. The output is CSV with a header row describing columns.

azuredatacatalog_run_query

Executes a SQL SELECT query against the connected data source and returns the resulting data set.