AWS adds automated cross-account migration for Amazon Quick resources
AWS has released a sample Model Context Protocol (MCP) server on Amazon Bedrock AgentCore to automate the promotion of Amazon Quick resources across AWS accounts. Previously, moving chat agents, action connectors, knowledge bases, flows, and spaces from development to production required manual recreation, a process that was error-prone and difficult to audit. The new solution uses the Amazon…
Key points
- AWS released a sample MCP server on Bedrock AgentCore to automate Amazon Quick resource migration.
- The tool is idempotent and creates versioned S3 backups before updates to allow for rollback.
- Permissions are copied programmatically via the Amazon Quick API, ensuring fidelity across accounts.
The migrator is idempotent, meaning it can be re-run safely to converge on the same state. It performs an upsert operation, creating new resources or updating existing ones, while copying permissions faithfully from the source. To ensure safety and auditability, the system writes versioned backups to Amazon S3 before any updates, allowing users to preview changes, review migration history, and roll back to previous versions if needed. Secret values in connectors are not copied; instead, placeholders are used, requiring re-authentication in the target account.
This approach addresses enterprise governance needs by providing a repeatable, least-privilege workflow. The solution runs on Amazon Bedrock AgentCore and can be driven via natural language in Amazon Quick or through a generated Quick App. The full source code is available in the aws-samples repository, enabling organizations to implement automated, auditable resource promotion without manual intervention.
The story so far
4 episodes →- AWS adds automated cross-account migration for Amazon Quick resourcesthis story
Making Amazon Quick enterprise-ready: Automated, auditable cross-account resource promotion
AWS Machine Learning Blog · 5 October 2026
Loading the full article…
This text was published by AWS Machine Learning Blog and written by Keshav Ganesh. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Enterprise & Industry
All →- Satya Nadella asks if Microsoft can lead AI again · 2 src
- Microsoft camouflages 20+ data centers as nature while signing 20-year gas deal · 1 src
- Microsoft report says AI accelerates cyberattacks · 1 src
- Anthropic brings Claude inference to India via Amazon Bedrock · 5 src
- MIT report finds only 34% of AI agent projects reach production due to knowledge gaps · 1 src
Comments
via GitHub Discussions