Frequently Asked Questions (FAQ) about Azure CLI MCP Server

Q: What is an MCP Server? A: MCP (Model Context Protocol) is an open protocol that standardizes how applications provide context to LLMs. An MCP Server acts as a bridge, allowing AI models to access and interact with external data sources and tools. The Azure CLI MCP Server wraps the Azure CLI, adding a user-friendly prompt and exposing it for AI interaction.

Q: What can I do with the Azure CLI MCP Server? A: You can use it to manage Azure resources using natural language. This includes listing resources, checking configurations, fixing security issues, and creating new resources. It essentially gives you AI-powered access to the full Azure CLI.

Q: Is it safe to use? A: Exercise caution! The MCP server is driven by an LLM, so validate the commands it generates before execution. Using a well-trained LLM like Claude 3.7 or GPT-4o improves safety, but always review commands. The software is provided “AS IS” without warranty.

Q: Is it secured for remote use? A: No. The current implementation is designed for local use only with the stio transport. It’s not secured for remote access and should not be run on a remote server in its current form.

Q: How do I install it? A: You can install it using Docker, Java, or via Smithery.ai. Docker and Java installations require some setup, while Smithery.ai offers a simpler, but third-party hosted, option.

Q: How do I install it with Docker? A: First, create an Azure Service Principal. Then, run the Docker container, providing the Service Principal credentials as an environment variable (AZURE_CREDENTIALS).

Q: How do I install it with Java? A: Install the Azure CLI and Java 17 or higher. Authenticate to Azure using az login. Download the latest JAR file from GitHub Releases and run it using java -jar.

Q: How do I use it with VS Code? A: Install GitHub Copilot and add the MCP Server using the VS Code command palette. Configure the server with the appropriate command (Docker or Java) and set GitHub Copilot to Agent mode.

Q: How do I use it with Claude Desktop? A: Add the server configuration to your claude_desktop_config.json file, specifying the command to run the server (Docker or Java).

Q: What is UBOS and how does this server relate to it? A: UBOS is a full-stack AI Agent Development Platform. You can integrate the Azure CLI MCP Server into UBOS to extend the capabilities of your AI Agents, allowing them to manage and automate Azure resources within the UBOS ecosystem.

Q: Where can I learn more about UBOS? A: Visit the UBOS website at https://ubos.tech to learn more about the platform and its features.