Seamlessly Integrate Azure Data Lake Storage Gen2 with LLMs via the Model Context Protocol

Unlock the power of your data lake for AI applications with the adls2-mcp-server, a robust and compliant implementation of the Model Context Protocol (MCP) for Azure Data Lake Storage Gen2 (ADLS2). This server acts as a crucial bridge, enabling Large Language Models (LLMs) to directly access and manipulate data within your ADLS2 environment, fostering a new era of AI-driven data interaction.

Getting Started

Prerequisites

• Python: Version 3.13 or higher is required.
• Azure Account: An active Azure subscription with an ADLS2 storage account.
• Azure CLI (Optional): Required for authentication if not using an account key.

Installation

Leverage the speed and efficiency of uv to install the adls2-mcp-server:

uv pip install adls2-mcp-server

Configuration

The adls2-mcp-server is designed for seamless integration with MCP-compatible applications like Claude Desktop.

Claude Desktop Integration

1. Locate Configuration File:

   • macOS: ~/Library/Application Support/Claude Desktop/claude_desktop_config.json
   • Windows: %APPDATA%\Claude Desktop\claude_desktop_config.json

2. Add MCP Server Configuration:

   Modify the claude_desktop_config.json file to include the following mcpServers configuration:

   {
       "mcpServers": {
           "adls2": {
               "command": "adls2-mcp-server",
               "env": {
                   "LOG_LEVEL": "DEBUG",
                   "UPLOAD_ROOT": "/path/to/store/uploads",
                   "DOWNLOAD_ROOT": "/path/to/store/downloads",
                   "AZURE_STORAGE_ACCOUNT_NAME": "your-azure-adls2-storage-account-name",
                   "READ_ONLY_MODE": "false"
               }
           }
       }
   }

   Environment Variables:

   | Variable | Description