Azure Data Lake Storage MCP Server By Cdata

🚀 CData's MCP Server for Azure Data Lake Storage

CData's Model Context Protocol (MCP) Server for Azure Data Lake Storage allows LLMs to query live data from Azure Data Lake Storage.

:heavy_exclamation_mark: 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).

🚀 Quick Start

We created this read - only MCP Server to enable LLMs (such as Claude Desktop) to query live data from Azure Data Lake Storage, which is supported by the CData JDBC Driver for Azure Data Lake Storage. The CData JDBC Driver connects to Azure Data Lake Storage by presenting them as relational SQL models. This server wraps the driver and makes the data accessible via a simple MCP interface, enabling LLMs to retrieve real - time information through natural language queries, eliminating the need for SQL.

✨ Features

• Allows LLMs to query live data from Azure Data Lake Storage.
• Wraps the CData JDBC Driver and provides a simple MCP interface.
• Enables natural - language queries without the need for SQL.

📦 Installation

Clone the repository

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

Build the server

mvn clean install

This will generate the JAR file: CDataMCP-jar-with-dependencies.jar.

Download and install the CData JDBC Driver

Download and install the CData JDBC Driver for Azure Data Lake Storage from https://www.cdata.com/drivers/azuredatalake/download/jdbc.

License the CData JDBC Driver

1. Navigate to the lib folder in the installation directory:
   • Windows: C:\Program Files\CData\CData JDBC Driver for Azure Data Lake Storage\
   • Mac/Linux: /Applications/CData JDBC Driver for Azure Data Lake Storage/
2. Run the command java -jar cdata.jdbc.adls.jar --license.
3. Enter your name, email, and "TRIAL" (or your license key).

Configure the connection to the data source

1. Run the command java -jar cdata.jdbc.adls.jar to open the Connection String utility.
2. Configure the connection string and click "Test Connection".

   ⚠️ Important Note

   If the data source uses OAuth, you need to authenticate in your browser.

3. Once the connection test is successful, copy the connection string for later use.

Create a .prp file

Create a .prp file (e.g., azure-data-lake-storage.prp) using the following properties and format:

Prefix=adls
ServerName=CDataADLS
ServerVersion=1.0
DriverPath=PATH\TO\cdata.jdbc.adls.jar
DriverClass=cdata.jdbc.adls.ADLSDriver
JdbcUrl=jdbc:adls:InitiateOAuth=GETANDREFRESH;
Tables=

💻 Usage Examples

Using the Server with Claude Desktop

Create the config file

Create the config file claude_desktop_config.json for Claude Desktop to add the new MCP server. If the file already exists, add the entry to the mcpServers section in the config file.

Windows

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

Linux/Mac

{
    "mcpServers": {
        "{classname_dash}": {
            "command": "/PATH/TO/java",
            "args": [
                "-jar",
                "/PATH/TO/CDataMCP-jar-with-dependencies.jar",
                "/PATH/TO/azure-data-lake-storage.prp"
            ]
        }
    }
}

Copy the config file

If necessary, copy the config file to the appropriate directory.

Windows

cp C:\PATH\TO\claude_desktop_config.json %APPDATA%\Claude\claude_desktop_config.json

Linux/Mac

cp /PATH/TO/claude_desktop_config.json /Users/{user}/Library/Application\ Support/Claude/claude_desktop_config.json

Run or refresh the client

Run or refresh your Claude Desktop client.

⚠️ Important Note

You may need to fully exit and re - open your Claude Desktop client for the MCP Servers to appear.

Running the Server

Run the following command to start the MCP Server:

java -jar /PATH/TO/CDataMCP-jar-with-dependencies.jar /PATH/TO/Salesforce.prp

⚠️ Important Note

The server uses stdio, so it can only be used with clients running on the same machine as the server.

Usage Details

Once the MCP Server is configured, the AI client can use the built - in tools to read, write, update, and delete the underlying data. Generally, you don't need to call the tools explicitly. Just ask the client questions about the underlying data system, for example:

• "What is the correlation between my closed won opportunities and the account industry?"
• "How many open tickets do I have in the SUPPORT project?"
• "Can you tell me what calendar events I have today?"

Tools & Descriptions

In the following definitions, {servername} refers to the name of the MCP Server in the config file (e.g., {classname_dash} above).

• {servername}_get_tables: Retrieves a list of tables available in the data source. Use the {servername}_get_columns tool to list available columns on a table. The output will be in CSV format, with the first line containing column headers.
• {servername}_get_columns: Retrieves a list of columns for a table. Use the {servername}_get_tables tool to get a list of available tables. The output will be in CSV format, with the first line containing column headers.
• {servername}_run_query: Execute a SQL SELECT query.

JSON - RPC Request Examples

If you're scripting requests to the MCP Server instead of using an AI client (e.g., Claude), you can refer to the following JSON payload examples (following the JSON - RPC 2.0 specification) when calling the available tools.

azure_data_lake_storage_get_tables

{
    "jsonrpc": "2.0",
    "id": 1,
    "method": "tools/call",
    "params": {
        "name": "azure_data_lake_storage_get_tables",
        "arguments": {}
    }
}

azure_data_lake_storage_get_columns

{
    "jsonrpc": "2.0",
    "id": 2,
    "method": "tools/call",
    "params": {
        "name": "azure_data_lake_storage_get_columns",
        "arguments": {
            "table":  "Account"
        }
    }
}

azure_data_lake_storage_run_query

{
    "jsonrpc": "2.0",
    "id": 3,
    "method": "tools/call",
    "params": {
        "name": "azure_data_lake_storage_run_query",
        "arguments": {
            "sql":  "SELECT * FROM [Account] WHERE [IsDeleted] = true"
        }
    }
}

📚 Documentation

Troubleshooting

1. If you can't see your CData MCP Server in Claude Desktop, make sure you've fully quit Claude Desktop (use the Task Manager on Windows or the Activity Monitor on Mac).
2. If Claude Desktop can't retrieve data, ensure that you've configured the connection correctly. Use the Connection String builder to create the connection string and copy it into the property (.prp) file.
3. If you have trouble connecting to your data source, contact the CData Support Team.
4. If you have trouble using the MCP server or have other feedback, join the CData Community.

📄 License

This MCP server is licensed under the MIT License. You're free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.

All Supported Sources