agent-bom discover aws
Discover AI Agents and MCP assets on AWS 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 aws. It is used for: Discover AI Agents and MCP assets on AWS and generate an inventory Full Skill content: https://321skill.com/skills/agent-bom-discover-aws-x-2/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 discovering and inventorying AI Agent and MCP-related assets within an AWS cloud environment. In practical development, operations and development personnel often need to understand what resources exist under their current account, such as Bedrock Agents, ECS services, SageMaker endpoints, Lambda functions, EKS clusters, Step Functions state machines, and EC2 instances. However, manual collection is time-consuming and prone to omissions.
Usage is straightforward: simply run the agent-bom discover-aws command in an environment configured with short-term AWS credentials (e.g., AWS SSO, WebIdentity, or STS). It automatically invokes the AWS SDK for read-only scanning, generates a JSON inventory file compliant with the agent-bom specification, and outputs it to the specified path. You can then optionally pass this inventory to agent-bom for further security scanning, dependency analysis, or policy assessment.
It is well-suited for operations engineers, agent developers, and full-stack engineers who need to manage AI infrastructure on AWS. It integrates seamlessly for teams already using agent-bom for asset management and compliance auditing. It is also highly useful for scenarios requiring a quick overview of AI asset distribution within an AWS account.
Before use, ensure Python 3.11+ and the agent-bom package are installed, and AWS credentials with read-only permissions are configured. Note that it performs discovery by default and does not automatically scan or upload data, ensuring credential security. It also supports specifying the AWS Profile and Region via environment variables, offering flexibility for multi-account environments.
Key Features
Unlike native AWS resource discovery tools (such as AWS Config or Resource Explorer), agent-bom-discover-aws is specifically tailored for AI Agent and MCP-related assets, outputs a standardized agent-bom inventory format, does not store long-term credentials, and performs all operations locally.
Limitations
Requires a Python 3.11+ environment, depends on the agent-bom package, and only supports obtaining short-term credentials via the AWS SDK credential chain (e.g., SSO, STS). It does not support direct use of long-term access keys.
FAQ
Are AWS administrator permissions required?
No, only read-only permissions are needed. Using an IAM read-only policy is recommended.
Which AWS regions are supported?
All regions are supported. It defaults to the region configured in the current credentials, which can be overridden by specifying the AWS_REGION environment variable.
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-2/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-2/raw/index.md