Frequently Asked Questions (FAQ) about ADLS2 MCP Server

Q: What is an MCP Server? A: MCP (Model Context Protocol) server acts as a bridge, allowing AI models to access and interact with external data sources and tools. It standardizes how applications provide context to LLMs.

Q: What is the ADLS2 MCP Server? A: The ADLS2 MCP Server is an implementation of the Model Context Protocol (MCP) specifically designed for Microsoft Azure Data Lake Storage Gen2 (ADLS2). It allows AI agents to interact with ADLS2.

Q: What is Azure Data Lake Storage Gen2 (ADLS2)? A: ADLS2 is a highly scalable and secure data lake solution offered by Microsoft Azure for storing massive amounts of data in various formats.

Q: What operations can I perform with the ADLS2 MCP Server? A: You can perform various file and directory operations, including listing filesystems, creating/deleting filesystems and directories, uploading/downloading files, renaming files/directories, getting file properties and metadata, and checking file/directory existence.

Q: What programming language is the ADLS2 MCP Server written in? A: The ADLS2 MCP Server is implemented in Python.

Q: What Python version is required to run the ADLS2 MCP Server? A: Python 3.13 or higher is required.

Q: How do I install the ADLS2 MCP Server? A: You can install it using uv: uv pip install adls2-mcp-server.

Q: How do I configure the ADLS2 MCP Server? A: The server is configured using environment variables, such as AZURE_STORAGE_ACCOUNT_NAME, UPLOAD_ROOT, DOWNLOAD_ROOT, and LOG_LEVEL. You can set these variables in your environment or in a .env file.

Q: How do I configure the ADLS2 MCP Server to work with Claude Desktop? A: You need to edit the claude_desktop_config.json file and add a configuration for the ADLS2 MCP Server, specifying the command to run the server and the required environment variables.

Q: What Azure authentication methods are supported? A: The server supports authentication using either an Azure Storage Account Key or Azure CLI credentials. If the AZURE_STORAGE_ACCOUNT_KEY is not set, the server will attempt to authenticate using Azure CLI.

Q: What is the purpose of the UPLOAD_ROOT and DOWNLOAD_ROOT environment variables? A: UPLOAD_ROOT specifies the root directory for file uploads to ADLS2, and DOWNLOAD_ROOT specifies the root directory for file downloads from ADLS2.

Q: What is the purpose of the READ_ONLY_MODE environment variable? A: READ_ONLY_MODE determines whether the server should operate in read-only mode. When set to true, the server will only allow read operations (e.g., downloading files) and prevent write operations (e.g., uploading files).

Q: How can I contribute to the ADLS2 MCP Server project? A: You can contribute to this Open Source Project. Fork the repository, create a branch for your feature or bug fix, commit your changes, and submit a pull request.

Q: Where can I find the claude_desktop_config.json file? A: On macOS, the file is located at ~/Library/Application Support/Claude Desktop/claude_desktop_config.json. On Windows, the file is located at %APPDATA%Claude Desktopclaude_desktop_config.json.

Q: What is UBOS, and how does it relate to the ADLS2 MCP Server? A: UBOS is a full-stack AI Agent Development Platform. It simplifies orchestrating AI Agents, connecting them with enterprise data, and building Multi-Agent Systems. The ADLS2 MCP Server enhances UBOS by enabling AI Agents to seamlessly access and manage data stored in Azure Data Lake Storage Gen2.

Q: How do I run the server locally for development? A: Clone the repository, create a virtual environment, install the dependencies, configure the environment variables, and then run the server using the specified command (e.g., uv run adls2-mcp-server).