agent-bom discover azure
Discover Azure AI assets and generate a standardized inventory
Install & Use
Copy this prompt and send it to your AI assistant (Claude / Cursor / TRAE / Codex / WorkBuddy etc.) to auto-install:
Help me install this AI Skill: agent-bom discover azure. It is used for: Discover Azure AI assets and generate a standardized inventory Full Skill content: https://321skill.com/skills/agent-bom-discover-azure-x-5/raw/index.md Read that page and install it.
The prompt includes a link to the full Skill content. You can also view the full content.
This Skill addresses the lack of a unified specification when inventorying AI Agent and MCP-related assets in the Azure cloud environment. In actual operations, teams often need to manually log into the Azure Portal or use multiple CLI commands to find resources such as Azure OpenAI, Container Apps, AKS, Functions, Machine Learning, etc. This makes it difficult to form a standardized asset inventory and can easily lead to missing critical information.
Usage is straightforward. You just need to ensure Python 3.11+ and the agent-bom package are installed locally, and you have Azure read-only identity (Azure CLI, Workload Identity, Managed Identity, or Service Principal all work). Run python examples/operator_pull/azure_inventory_adapter.py --subscription-id "$AZURE_SUBSCRIPTION_ID" --output azure-inventory.json to automatically discover assets and generate a standardized JSON. Afterwards, you can use natural language instructions to have agent-bom scan this inventory and obtain security analysis results.
It is well-suited for operations teams and agent developers who need to regularly audit Azure AI infrastructure. Especially for organizations already using agent-bom for Bill of Materials (BOM) management, this discovery capability can be seamlessly integrated without providing agent-bom with long-term Azure credentials, thereby reducing security risk.
It is recommended to use this tool uniformly in CI/CD pipelines or regular inspection tasks. Note that it primarily performs read-only discovery operations and will not modify any Azure resources; the generated inventory JSON should be securely stored to avoid leaking subscription information.
Key Features
Unlike Azure Resource Graph or the Azure CLI's `az resource list`, `agent-bom-discover-azure` specifically filters for AI Agent and MCP-related assets (such as Azure OpenAI, Container Apps, AKS, Functions, ML, etc.), outputs standardized JSON compliant with the `agent-bom` specification, and supports a secure scanning mode without long-term credentials.
Limitations
Requires a Python 3.11+ environment, depends on Azure SDK libraries, and must have read-only permissions to an Azure subscription (obtained via Azure CLI, Workload Identity, Managed Identity, or Service Principal). Anonymous discovery without identity is not supported.
FAQ
What dependencies does this Skill require?
It requires Python 3.11+, the `agent-bom` package (installable from PyPI: `pip install agent-bom`), and Azure CLI or equivalent identity authentication. No additional Azure SDK installation is needed; `agent-bom` handles it automatically.
What scenarios can the generated inventory JSON be used for?
It can be used for asset auditing, security scanning, cost analysis, compliance reporting, etc. You can import the JSON file into `agent-bom` for scanning or integrate it with other tools. Note that the JSON does not contain credential information, making it secure and reliable.
Installation guide for AI assistants
If your AI coding assistant (Claude Code, Cursor, TRAE etc.) can see this page, send it this message to auto-install:
Visit https://321skill.com/skills/agent-bom-discover-azure-x-5/raw/index.md to read the original Skill definition (Markdown format) for agent-bom discover azure, and install it according to the instructions.
Raw Markdown URL for AI: /skills/agent-bom-discover-azure-x-5/raw/index.md