View a markdown version of this page

Data protection in Amazon Agent Registry - Amazon Bedrock AgentCore
Validate record metadata before you act on it
Services or capabilities described in Amazon Web Services documentation might vary by Region. To see the differences applicable to the China Regions, see Getting Started with Amazon Web Services in China (PDF).

Data protection in Amazon Agent Registry

The Amazon shared responsibility model applies to data protection in Amazon Agent Registry. As described in this model, we are responsible for protecting the global infrastructure that runs all of the Amazon Cloud. You are responsible for maintaining control over your content that is hosted on this infrastructure. This content includes the security configuration and management tasks for the Amazon services that you use. For more information about data privacy, see the Data Privacy FAQ on the Amazon website.

For data protection purposes, we recommend that you protect Amazon account credentials and set up individual user accounts with IAM. That way each user is given only the permissions necessary to fulfill their job duties. We also recommend that you secure your data in the following ways:

  • Use multi-factor authentication (MFA) with each account.

  • Use SSL/TLS to communicate with Amazon resources.

  • Set up API and user activity logging with Amazon CloudTrail.

  • Use Amazon encryption solutions, along with all default security controls within Amazon services.

  • Use advanced managed security services such as Amazon Macie, which assists in discovering and securing personal data that is stored in Amazon S3.

We strongly recommend that you never put sensitive identifying information, such as your customers' account numbers, into free-form fields such as a Name field. This includes when you work with Amazon Agent Registry or other Amazon services using the console, API, Amazon CLI, or Amazon SDKs. Any data that you enter into Amazon Agent Registry or other services might get picked up for inclusion in diagnostic logs. When you provide a URL to an external server, don’t include credentials information in the URL to validate your request to that server.

Validate record metadata before you act on it

Publishers provide record metadata, including package identifiers, repository URLs, and remote endpoint URLs. Amazon Agent Registry checks this metadata only against the schema for the record’s descriptor. It doesn’t verify the packages, repositories, or endpoints that a record references. Under the Amazon shared responsibility model, you are responsible for validating these fields. Validate them before your agent installs, downloads, or connects to anything a record references, in the same way you validate input from any external source. For the fields that each descriptor supports, see Supported record types and descriptors.

To validate record metadata, use patterns such as the following:

  • Install packages only from an allowlist or from a package repository that you control, such as Amazon CodeArtifact, and pin each package to a specific version.

  • Download source code only from repository hosts and owners that you allow.

  • Connect only to MCP server endpoints whose URL scheme and domain you allow.

Topics