agent-bom discover gcp
Discover AI Agent and MCP assets on GCP and generate an 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 gcp. It is used for: Discover AI Agent and MCP assets on GCP and generate an inventory. Full Skill content: https://321skill.com/skills/agent-bom-discover-gcp-x-4/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 inventorying AI assets on GCP. In practice, operations and development teams often need to manually catalog resources like Vertex AI, Cloud Run, Cloud Functions, and GKE. Manual processes are time-consuming and prone to omissions, especially when standardized inventories are required for auditing, migration, or cost analysis, and a unified tool is lacking. This Skill automatically discovers these assets and outputs a standardized agent-bom JSON format, requiring no long-term credentials, ensuring security and efficiency.
Usage is straightforward. You only need to configure Application Default Credentials (ADC) or workload identity in your GCP environment, then run the provided Python script (e.g., gcp_inventory_adapter.py), specifying the project and region. You can then trigger the inventory via natural language instructions. The AI agent will automatically call GCP APIs, collect asset information, and write it to your specified JSON file. The entire process requires no manual API coding and does not expose credentials to third parties.
It is ideal for teams or individuals managing AI infrastructure on GCP, especially operations engineers, agent developers, and project managers. Teams already using agent-bom for asset management can seamlessly integrate this discovery capability to achieve automated inventory. For scenarios requiring regular GCP resource audits, cloud migration, or building asset catalogs, this Skill significantly improves efficiency.
It is recommended to use this tool uniformly in CI/CD pipelines or regular inspections, e.g., running it automatically weekly and comparing inventory changes. Note that it primarily relies on GCP read-only permissions and will not modify any resources. Also, credential information is not leaked to the agent-bom service; all operations are performed locally. Ensure Python version ≥ 3.11 and install the agent-bom library in advance. For a large number of projects, consider executing in batches to avoid API rate limits.
Key Features
Unlike manually using gcloud commands or the GCP Console for item-by-item inventory, this Skill automatically generates a standardized JSON inventory compliant with the agent-bom specification. It does not require exposing long-term credentials to third-party services, as all discovery operations are executed locally, offering higher security. While similar tools like `gcloud asset list` can also list resources, their output format is not standardized and cannot integrate directly with the agent-bom ecosystem.
Limitations
Requires Python 3.11+, depends on the agent-bom library (installable via pip), supports only GCP environments, and requires GCP read-only credential configuration (ADC, workload identity, or temporary service account). It does not support other cloud platforms.
FAQ
What dependencies does this Skill require?
Requires Python 3.11+ and the agent-bom library, installable via `pip install agent-bom`.
Does it require GCP administrator permissions?
No, only project-level read-only permissions (e.g., roles/viewer) are needed, provided via Application Default Credentials or workload identity.
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-4/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-4/raw/index.md