agent-bom discover gcp
Inventory of AI Agent and MCP Assets on GCP
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 of AI Agent and MCP Assets on GCP Full Skill content: https://321skill.com/skills/agent-bom-discover-gcp/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 systematically discovering and inventorying AI Agent and MCP-related assets within a GCP environment. Many teams lack a unified, standardized inventory format when managing resources like Vertex AI, Cloud Run, Cloud Functions, and GKE, leading to fragmented asset information that is difficult to audit and analyze subsequently. This tool automatically scans GCP projects and generates a standardized agent-bom inventory JSON.
Usage is straightforward: simply run the python examples/operator_pull/gcp_inventory_adapter.py script locally, specifying the project ID, region, and source identifier via parameters. It leverages your existing GCP read-only credentials (ADC, Workload Identity, or a restricted service account) to call Google APIs, discover all AI and MCP-related assets, and output a compliant inventory JSON file. You can then choose whether to import this inventory into agent-bom for scanning.
It is ideal for teams or individuals needing to inventory AI infrastructure on GCP, especially developers already using the agent-bom ecosystem for asset management and compliance auditing. Operations engineers can quickly obtain a global resource view, AI agent developers can verify the online status of dependent MCP services, and project managers can make decisions based on the standardized inventory.
We recommend using this tool during the initial setup of GCP projects or for regular audits. Note that it only supports the GCP platform and requires a Python 3.11+ environment with the agent-bom library installed. Support for other cloud providers like AWS or Azure is not currently available.
Key Features
Unlike Google Cloud Asset Inventory, it specifically focuses on AI Agent and MCP-related assets (such as Vertex AI models, Cloud Run services, GKE clusters) and outputs a standardized JSON compliant with the agent-bom specification, facilitating subsequent cross-toolchain integration and automated scanning.
Limitations
Requires Python 3.11+, installation of the agent-bom library, and only supports the GCP platform. Read-only GCP credentials (ADC/Workload Identity/service account) are required.
FAQ
How do I install agent-bom-discover-gcp?
Install the agent-bom library via pip: `pip install agent-bom`. The script is located in the project's `examples/operator_pull/` directory.
What GCP permissions are required?
Project-level read-only permissions are required. It is recommended to use Application Default Credentials, Workload Identity, or a restricted service account. Do not directly paste service account JSON into the chat.
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/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/raw/index.md