agent-bom discover aws
Discover AI agents and MCP assets on AWS and generate a standardized 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 aws. It is used for: Discover AI agents and MCP assets on AWS and generate a standardized inventory. Full Skill content: https://321skill.com/skills/agent-bom-discover-aws-x-9/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 quickly inventorying AI Agent and MCP-related assets within the AWS cloud environment. In day-to-day operations, teams often need to identify which resources across services like AWS Bedrock, ECS, SageMaker, Lambda, EKS, Step Functions, and EC2 are AI-related. Manually gathering this scattered information is time-consuming and prone to oversight. By making read-only calls to the AWS SDK, this skill automatically discovers and outputs a standardized agent-bom inventory JSON, making asset inventory efficient and reliable.
Usage is straightforward. Simply install the agent-bom library in an environment with configured AWS credentials (AWS SSO, WebIdentity, or STS temporary credentials are recommended) and run the agent-bom discover aws command. It automatically scans all supported regions in the current account, collects AI Agent and MCP-related resources, and generates a canonical inventory JSON file. You can then optionally pass this inventory to agent-bom for further scanning, dependency graph generation, or policy analysis—this step is entirely up to you.
It's ideal for operations engineers and agent development teams managing multi-cloud AI assets, especially organizations that have already deployed multiple AI services on AWS (such as Bedrock Agent, SageMaker endpoints, Lambda functions). This skill enables them to quickly obtain a unified, formatted asset list, laying the groundwork for subsequent compliance audits, cost optimization, and security scanning.
It's recommended to run this tool after any AI asset changes to keep the inventory up-to-date. Note that it only supports the AWS platform and requires a Python 3.11+ environment. Credentials must have read-only permissions to avoid security risks from excessive privileges. The generated JSON file does not contain sensitive information by default, but it's advised to store it in a secure location.
Key Features
Unlike AWS Config or custom scripts, this skill is specifically designed for AI Agent and MCP assets, outputs in the standardized agent-bom format, and does not require long-term credentials. It performs scans using STS temporary credentials, reducing the risk of credential exposure.
Limitations
Requires Python 3.11+ and the agent-bom library. It only supports the AWS SDK credential chain, does not support other cloud platforms, and can only discover resources for which read-only authorization is granted.
FAQ
What AWS permissions are required?
Read-only permissions are required. It is recommended to use AWS SSO, WebIdentity, or STS temporary credentials, avoiding long-term access keys.
How do I install it?
Run `pip install agent-bom` to install, then execute the `agent-bom discover aws` command.
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-aws-x-9/raw/index.md to read the original Skill definition (Markdown format) for agent-bom discover aws, and install it according to the instructions.
Raw Markdown URL for AI: /skills/agent-bom-discover-aws-x-9/raw/index.md