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-9/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 challenge of uniformly inventorying AI Agent and MCP-related assets within the Azure cloud environment. In practice, operations and development teams often need to manually log into the Azure Portal or use multiple CLI commands to locate resources such as Azure OpenAI, Container Apps, AKS, Functions, and ML services. The lack of a standardized inventory format complicates subsequent auditing and scanning processes.
Usage is straightforward: ensure you have Azure read-only permissions via Azure CLI, workload identity, or managed identity, then run a single Python command. It automatically invokes the Azure SDK for read-only discovery and outputs the results as a standardized agent-bom inventory JSON file. You can then use natural language instructions to have agent-bom scan this inventory for security or compliance findings.
It is well-suited for operations teams and agent developers who need to regularly inventory Azure AI infrastructure. Organizations already using agent-bom as their unified asset inventory standard can integrate this seamlessly into existing workflows without developing custom scripts for Azure.
It is recommended to use this tool uniformly within CI/CD pipelines or regular inspection tasks. Note that it primarily relies on the operator's existing Azure identity chain, does not store long-term credentials, but requires a Python 3.11+ environment and the installation of the agent-bom library.
Key Features
Unlike Azure Resource Graph queries or manual exports, it directly generates a standardized inventory JSON compliant with the agent-bom specification. It does not require long-term Azure credentials, instead reusing the operator's existing identity chain (Azure CLI, managed identity, etc.), making it more secure and easier to integrate into the agent-bom ecosystem.
Limitations
Requires a Python 3.11+ environment, installation of the agent-bom library (`pip install agent-bom`), and the operator must possess Azure read-only permissions (via Azure CLI, workload identity, managed identity, or service principal).
FAQ
What Azure permissions are required?
Only Azure read-only permissions are needed. It is recommended to use Azure CLI login, workload identity, or managed identity; long-term client secrets are not required.
How do I install agent-bom?
Run `pip install agent-bom`. The tool is published on PyPI.
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-9/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-9/raw/index.md