agent-bom discover gcp
Inventory GCP AI and MCP Assets to Generate a Standardized Bill of Materials (BOM)
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 gcp. It is used for: Inventory GCP AI and MCP Assets to Generate a Standardized Bill of Materials (BOM) Full Skill content: https://321skill.com/skills/agent-bom-discover-gcp-x-10/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 scattered and difficult-to-unify inventory of AI Agent and MCP-related assets on GCP. In practical operations, resources like Vertex AI, Cloud Run, Cloud Functions, and GKE are distributed across multiple projects and services, making manual inventory inefficient and prone to omissions. This tool automatically discovers these assets and generates a standardized inventory JSON compliant with the agent-bom specification, providing a unified data foundation for subsequent asset scanning, compliance audits, and cost analysis.
Usage is straightforward: simply install the agent-bom tool locally and configure GCP read-only credentials (such as Application Default Credentials or Workload Identity). Then, a single command specifying the project ID and region triggers the auto-discovery process. The tool calls GCP read-only APIs to fetch resource information and ultimately writes the standardized inventory JSON to your specified file path. The entire process does not expose long-term credentials to third-party services.
It is ideal for DevOps engineers, agent developers, and cloud architects who need unified management of AI infrastructure on GCP. Teams already using the agent-bom ecosystem for asset inventory management can seamlessly integrate it into their existing scanning and analysis pipelines. For organizations requiring regular inventory of cloud-based AI resources to ensure asset visibility, this is an efficient automation solution.
It is recommended to use this tool uniformly within CI/CD pipelines or scheduled tasks to periodically generate and archive asset snapshots. Note that it only supports the GCP platform and requires a Python 3.11+ environment. For credentials, always use short-lived, read-only permissions and avoid exposing service account JSON keys directly in conversations or logs.
Key Features
Unlike general-purpose resource discovery tools like `gcloud asset list`, this tool specifically filters for AI Agent and MCP-related assets (such as Vertex AI, Cloud Run, GKE) and outputs JSON in the standard agent-bom format. This output can be directly used for subsequent agent-bom scanning and analysis without requiring additional conversion.
Limitations
Requires a Python 3.11+ environment, agent-bom to be installed, and depends on GCP read-only credentials (ADC or Workload Identity). It only supports the GCP platform and does not support multi-cloud environments.
FAQ
How do I install agent-bom-discover-gcp?
Install the agent-bom package via pip: `pip install agent-bom`. Alternatively, clone the GitHub repository and install it locally.
What GCP permissions are required?
Only read-only permissions are needed. It is recommended to use Application Default Credentials or Workload Identity; long-term service account keys are not required. Read-only access to the following APIs is needed: cloudresourcemanager, aiplatform, run, cloudfunctions, container.
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-gcp-x-10/raw/index.md to read the original Skill definition (Markdown format) for agent-bom discover gcp, and install it according to the instructions.
Raw Markdown URL for AI: /skills/agent-bom-discover-gcp-x-10/raw/index.md