AWS Agent Registry adds custom metadata schemas for governance
Start here
AWS Agent Registry now supports custom metadata schemas, letting administrators define key-value fields that every registered agent, MCP server and skill record must follow. Records created without any custom metadata are saved as NON_COMPLIANT and cannot be submitted for approval, while records with an unknown field, a missing required field or an invalid value are rejected with a ValidationException. The indexed metadata enables filtering such as environment=prod AND businessUnit=payments AND securityScanStatus=PASSED. Only approved records are returned, so a record that matches the filters but has not been approved stays out of the results. The feature requires an AWS account in a supported AWS Region.
Generated from reports · updated 4 h ago
Report timeline
Follow the reports to see the event from different sides.
- AWS Machine Learning BlogAWS Agent Registry adds custom metadata schemas for agent governance
AWS Agent Registry now supports custom metadata schemas, letting administrators define key-value fields that every registered agent, MCP server, and skill record must follow. Records missing required fields are saved as NON_COMPLIANT and cannot be submitted for approval, while invalid values are rejected with a ValidationException. The indexed metadata enables filtering such as environment=prod AND businessUnit=payments AND securityScanStatus=PASSED, with only approved records returned.
Heat for this event
- Current, comparable range
- 9
- Peak, comparable range
- 10November 18 05:00
- Change in 24 hours
- –
The trend compares the same participants over hours observed continuously, so its range can be narrower than the current heat count. Hover or tap the chart for hourly heat; the arrow keys move through it.