agent-bom discover azure

This Skill addresses the challenge of uniformly inventorying AI Agent and MCP-related assets within the Azure cloud environment. In practice, operations engineers and agent developers often need to quickly identify AI infrastructure—such as OpenAI services, container apps, AKS clusters, function apps, and machine learning workspaces—under an Azure subscription. Manual queries are time-consuming, prone to omissions, and produce inconsistent output formats across different tools, making automation difficult.

Usage is straightforward: simply run a single Python command in an environment where Azure CLI is already logged in or workload identity is configured. It automatically invokes the Azure SDK for read-only discovery and outputs the results as a JSON inventory file compliant with the agent-bom specification. You can then use natural language instructions to have agent-bom scan this inventory for security and compliance analysis. The entire process does not require providing long-term Azure credentials to agent-bom.

This Skill is ideal for operations engineers and agent development teams that need to regularly inventory Azure AI resources. Organizations already using agent-bom for asset inventory management can seamlessly integrate Azure assets into a unified view. For scenarios requiring compliance audits or aiming to automate infrastructure discovery workflows, this Skill significantly improves efficiency.

It is recommended to use this tool to generate the latest inventory before and after major deployments or on a regular schedule (e.g., weekly). Note that it primarily relies on Azure read-only identity chains (Azure CLI, managed identities, etc.). Ensure the execution environment has the correct permissions configured. The output file path is specified by the operator; please securely store the generated JSON file to avoid exposing subscription information.