agent-bom discover azure

This Skill addresses the challenge of uniformly inventorying AI Agent and MCP-related assets within the Azure cloud environment. In practical operations, teams often need to manually log into the Azure Portal or write temporary scripts to locate resources such as Azure OpenAI, Container Apps, AKS clusters, Function Apps, and Machine Learning workspaces. This approach is not only inefficient but also prone to missing critical assets, and storing Azure credentials long-term poses security risks.

Usage is straightforward. You simply need to ensure Python 3.11+ and the agent-bom library are installed locally, and you have obtained read-only permissions via Azure CLI, workload identity, or managed identity. You can then trigger the discovery process using natural language instructions, such as requesting an inventory of AI assets under the current subscription. This Skill will call the Azure SDK for read-only queries, generate a JSON inventory file compliant with the agent-bom specification, and by default, it will stop at the discovery phase without performing automatic scanning or uploading.

It is ideal for operations engineers and agent development teams that require regular auditing of Azure AI infrastructure. Organizations already using the agent-bom ecosystem for asset inventory management can seamlessly integrate discovery results from Azure into their unified inventory, avoiding redundant work. For scenarios with high security and compliance requirements, the Skill's design ensures credentials never leave the operator's environment, outputting only a sanitized inventory.

It is recommended to use this tool uniformly after each Azure resource change or during periodic inspections. Note that it primarily relies on Azure Resource Manager and Cognitive Services APIs; some resource types (like custom MCP servers) may require additional configuration for identification. Before first use, confirm Python version ≥3.11 and install the agent-bom library.