AWS Agent Registry launches custom metadata schema
Understand this story
AWS Agent Registry adds a custom metadata schema: administrators can define field names, types, allowed values, and required fields, and all records in the registry must conform to that schema. Records missing required fields, or containing unknown fields or invalid values, are rejected with a ValidationException; records without custom metadata are marked as NON_COMPLIANT. The feature is available to AWS accounts in supported AWS Regions, requires Python 3.11 or later and boto3 1.43.113 or later to use, and the example implementation is in a GitHub repository.
AI overview based on source reports · Updated 4 hr ago
Coverage timeline
Follow the coverage to explore different perspectives.
- AWS Machine Learning BlogGovern and discover records with common metadata in AWS Agent Registry
AWS Agent Registry now supports custom metadata schemas, organization-defined key-value fields that an administrator applies to a registry so every record must conform, with values validated on create or update and non-conforming records rejected with a ValidationException. The post walks through an example MCP server record, covering schema definition, registration, enrichment by existing security and CMDB tooling, approval via an EventBridge-triggered Lambda function, and discovery through search filters or the registry's MCP endpoint. It also advises treating the schema as a shared vocabulary, noting that changes are additive and existing records are not rewritten.
Activity for this story
- Current comparable activity
- 9
- Peak comparable activity
- 10Nov 18 05:00
- Change in the past 24 hours
- –
Trends compare the same fully observed participants, which may cover fewer participants than current activity. Move the pointer or tap the chart to inspect hourly activity; use the left and right arrow keys with a keyboard.