agent-bom discover gcp
Inventorying 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: Inventorying AI Agent and MCP Assets on GCP Full Skill content: https://321skill.com/skills/agent-bom-discover-gcp-x-3/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 challenges of inventorying AI assets and managing credentials in GCP cloud environments. In practice, DevOps engineers and AI agent developers often need to quickly identify resources related to AI Agents and MCP within a project—such as Vertex AI endpoints, Cloud Run services, Cloud Functions, and GKE clusters—without exposing long-term GCP credentials to third-party tools. They also require a structured, standardized inventory for subsequent auditing or scanning.
Usage is straightforward. Ensure you have Python 3.11+ and the agent-bom library installed locally, and configure read-only GCP credentials such as Application Default Credentials (ADC) or Workload Identity. Then, execute the discovery with a single command: python examples/operator_pull/gcp_inventory_adapter.py --project $GOOGLE_CLOUD_PROJECT --region us-central1 --source gcp-skill-invoked. The script automatically calls GCP read-only APIs, gathers relevant resource information, and outputs a canonical inventory JSON file compliant with the agent-bom specification to the specified path.
This Skill is ideal for teams or individuals who need unified management of AI infrastructure on GCP. It is particularly useful for DevOps engineers, AI agent developers, and cloud architects already using the agent-bom ecosystem for asset scanning, security auditing, or cost analysis. For scenarios requiring regular multi-cloud inventory while adhering to the principle of least privilege for credentials, this Skill provides an out-of-the-box solution.
Before first use, ensure your GCP read-only credentials are correctly configured and permissions are granted only to the projects you need to inventory. Note that the Skill primarily relies on the GCP SDK for local discovery and does not send data to any external services; credentials remain within the operator's environment. Sensitive information (e.g., keys) in the output JSON is automatically redacted, making it suitable for direct use in subsequent agent-bom scans or persistent storage.
Key Features
Unlike using the gcloud CLI directly or custom scripts, this Skill outputs a standardized agent-bom inventory JSON format that can be directly consumed by tools in the agent-bom ecosystem. Additionally, it does not require providing long-term GCP credentials to the agent-bom service; all API calls are performed locally, and credentials are used solely for read-only discovery.
Limitations
Requires a Python 3.11+ environment and the agent-bom library must be pre-installed (available via PyPI or GitHub). It only supports the GCP platform and is not compatible with AWS or Azure. Relies on the operator's GCP read-only credentials (ADC, Workload Identity, or short-lived service accounts).
FAQ
How do I install agent-bom?
Run `pip install agent-bom` to install from PyPI, or clone the GitHub repository at https://github.com/msaad00/agent-bom for local installation.
Do I need to install gcloud CLI in advance?
It is not mandatory but recommended for managing ADC credentials. If the GOOGLE_APPLICATION_CREDENTIALS environment variable is configured or Workload Identity is used, gcloud is not required.
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-3/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-3/raw/index.md