En

agent-bom discover gcp

Inventory GCP AI and MCP Assets to Generate a Standardized List

开发流程 盘点GCP AI与MCP资产生成清单 通用 ★ 2.7k Updated 2026-08-02

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 List
Full Skill content: https://321skill.com/skills/agent-bom-discover-gcp-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 challenge of uniformly inventorying AI Agent and MCP-related assets on GCP. In practical development, teams often need to audit resources like Vertex AI, Cloud Run, Cloud Functions, and GKE, but lack a standardized inventory format and a read-only, secure discovery method.

Usage is straightforward: simply install the agent-bom package in a Python 3.11+ environment and ensure GCP Application Default Credentials or Workload Identity is configured. You can then trigger the discovery process using natural language instructions. The script will call GCP's read-only APIs, output the discovered assets as a standardized agent-bom inventory JSON file, and write it to your specified path.

It is ideal for DevOps engineers, agent developers, and project managers who need to manage GCP AI infrastructure. This is especially true for teams that have already deployed multiple AI Agents or MCP services and require regular asset inventory checks, compliance audits, or migration assessments.

We recommend integrating this tool into your CI/CD pipeline or periodic inspection tasks. Note that it primarily relies on the operator's existing GCP read-only credentials, does not request long-term keys, and only performs discovery operations without modifying any resources.

Key Features

Unlike Google Cloud Asset Inventory, it specifically targets AI Agent and MCP-related resources (Vertex AI, Cloud Run, Cloud Functions, GKE), outputs in the standardized agent-bom inventory format, and requires no long-term credentials, directly reusing the operator's existing ADC or Workload Identity.

Limitations

Requires Python 3.11+, depends on GCP read-only credentials (ADC or Workload Identity), supports only the GCP platform, and does not support other cloud providers.

FAQ

How do I install this Skill?

Run `pip install agent-bom` to install, then invoke it via a Python script or AI assistant.

What permissions are required?

GCP read-only permissions are required, provided via Application Default Credentials, Workload Identity, or short-lived service accounts; no long-term keys are needed.

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-5/raw/index.md to read the original Skill definition (Markdown format) for agent-bom discover gcp, and install it according to the instructions.