← Back to all announcements
★★★★☆ 27/05/2026

Amazon Aurora MySQL now supports integration with Kiro Powers

Chat your way through Aurora MySQL cluster setup, schema design, and RDS migrations—no SQL syntax or AWS API expertise required.

View original announcement →

Visual Summary

graph TD A{{Aurora MySQL Kiro Powers}}:::announced B((Developer)):::external C(Kiro IDE):::compute D([MCP Server]):::feature E([Steering Files]):::feature F(Amazon Aurora MySQL):::storage G([Dynamic Context Loading]):::feature H([Migration Guidance]):::feature I(Amazon RDS MySQL):::storage B ==>|"natural language"| C C ==>|"activates"| A A -->|"connects via"| D A -->|"loads best practices"| E D -->|"queries & manages"| F G -.->|"task-relevant guidance"| A A -->|"migration path"| H H -->|"promotes replica"| I I -.->|"migrates to"| F classDef announced fill:#ff9900,stroke:#ec7211,color:#fff,font-weight:bold classDef compute fill:#e3f2fd,stroke:#1565c0,color:#1565c0 classDef storage fill:#e8f5e9,stroke:#2e7d32,color:#2e7d32 classDef feature fill:#fff3e0,stroke:#e65100,color:#e65100 classDef external fill:#f5f5f5,stroke:#616161,color:#616161

What's New

Amazon Aurora MySQL-Compatible Edition now integrates with Kiro Powers, a curated repository of pre-packaged Model Context Protocol (MCP) servers, steering files, and hooks validated by Kiro partners. This integration gives developers AI-assisted access to both data plane operations (queries, schema management) and control plane operations (cluster creation, management) through natural language in the Kiro IDE. The Aurora MySQL MCP Server bundles live database connectivity with Aurora-specific best practices, enabling faster application development without requiring deep expertise in Aurora syntax or APIs.

How It Works

  • Kiro Powers packaging: The Aurora MySQL Power combines an MCP server (for live AWS API and database access), steering files (encoding Aurora MySQL best practices curated by domain experts), and optional validation hooks that flag configuration issues before deployment.
  • Natural language to operations: Developers describe what they need in plain language; the Kiro agent translates requests into SQL queries, AWS API calls, or configuration commands for review and execution—covering both data plane (SELECT, CREATE TABLE, schema changes) and control plane (cluster provisioning, parameter group management) operations.
  • Dynamic context loading: Rather than loading all Aurora documentation at once, the agent dynamically activates only task-relevant guidance—such as Serverless v2 scaling policies, RDS-to-Aurora migration runbooks, or replication configuration—based on the active conversation context.
  • MCP server connectivity: The underlying awslabs.mysql-mcp-server connects via RDS Data API or direct MySQL wire protocol, supporting Aurora MySQL, RDS MySQL, and MariaDB endpoints, and requires local AWS credentials configured via aws configure or environment variables.
  • One-click installation: The Power is installable directly from the Kiro IDE or the Kiro web portal; Kiro handles all configuration and setup automatically, making the capability available within seconds.
  • Migration guidance: For RDS MySQL to Aurora MySQL migrations, the Power walks through four structured phases—assess, migrate (read replica promotion for near-zero downtime), promote, and post-cutover validation—generating the specific commands at each step.

Why It's Important

  • Lowers the expertise barrier: Developers unfamiliar with Aurora-specific syntax, parameter groups, or migration procedures can now accomplish complex database operations through conversational commands, reducing reliance on specialized DBAs for routine tasks.
  • Accelerates migration projects: Production migrations from RDS MySQL to Aurora MySQL typically require multi-week efforts covering compatibility audits, parameter reconciliation, and cutover runbooks; the Power compresses this by automating assessment and generating validated commands at each phase.
  • Reduces cognitive load: Dynamic context loading ensures developers receive only the guidance relevant to their current task (e.g., Serverless scaling vs. replication config), preventing information overload that slows decision-making.
  • Integrates AI into the database development loop: By embedding Aurora expertise directly into the IDE where code is written, AWS closes the gap between application development and database operations, enabling a more unified developer workflow.
  • Validated best practices at scale: Steering files encode AWS-curated Aurora MySQL standards, meaning AI-generated recommendations follow current production-grade patterns rather than generic LLM outputs that may be outdated or incorrect.

How It's Different

  • Beyond generic MCP database tools: Unlike generic database MCP servers that only translate natural language to SQL, the Aurora MySQL Power adds Aurora-specific control plane operations (cluster creation, Serverless scaling, replication) and curated steering files that encode AWS best practices—not just query execution.
  • Dynamic vs. static context: Competing approaches often load all available documentation into the model context window at once; Kiro Powers activate only task-relevant guidance dynamically, keeping the agent focused and reducing token overhead.
  • Validated partner ecosystem: Powers are validated by Kiro partners before publication, distinguishing them from community MCP servers that may lack production-quality guidance or security review.
  • IDE-native experience: The integration lives inside the Kiro IDE (and Kiro Web), meaning database operations, code generation, and infrastructure management happen in a single environment rather than requiring context-switching between tools like the AWS Console, CLI, and a code editor.
  • Structured migration workflow: The Power provides a phased, opinionated migration path (assess → migrate → promote → validate) rather than leaving developers to assemble their own migration approach from documentation fragments.

When to Prefer It

  • Migrating from RDS MySQL to Aurora MySQL: Teams planning a production migration who need compatibility assessment, method selection (snapshot vs. read replica promotion), parameter group translation, and post-cutover validation without building a custom runbook from scratch.
  • Greenfield Aurora MySQL application development: Developers starting a new Aurora-backed application who want schema design guidance, cluster provisioning, and query generation through natural language rather than learning Aurora-specific APIs and SQL dialects.
  • Aurora Serverless v2 configuration: Teams adopting Aurora Serverless v2 who need guidance on ACU scaling policies, minimum/maximum capacity settings, and cost optimization without deep familiarity with Serverless-specific parameters.
  • Small teams without dedicated DBAs: Engineering teams that lack database specialists and need AI-assisted expertise for schema design, index recommendations, replication setup, and operational tasks.
  • Rapid prototyping and iteration: Developers who need to spin up Aurora clusters, create schemas, and run exploratory queries quickly during early-stage development without context-switching to the AWS Console or CLI.
  • Kiro IDE users already in the ecosystem: Teams already using Kiro for application development who want to extend AI assistance to their database layer with minimal additional setup (one-click install).

Availability

  • General Availability: This integration is generally available as of May 27, 2026.
  • Regional availability: Available in all AWS Regions where Amazon Aurora MySQL is supported; cluster creation and management operations are region-scoped per standard Aurora availability.
  • Installation: One-click installation via the Kiro IDE or the Kiro web portal (kiro.dev/powers/); the underlying MCP server (awslabs.mysql-mcp-server) is also available as an open-source AWS Labs package installable via uvx.
  • Prerequisites: Requires a Kiro account (IDE or Web), local AWS credentials with appropriate IAM permissions for RDS/Aurora APIs, Python 3.10+ (for the MCP server), and uv from Astral for package management.
  • Pricing: Aurora MySQL usage is billed at standard Aurora pricing; Kiro IDE has its own subscription tiers (Free, Pro, Pro+, Power); no additional charge is listed specifically for the Aurora MySQL Power itself.
  • Limitations: The MCP server must currently run locally on the same host as the LLM client; write queries require explicit --allow_write_query flag to be enabled; Kiro Web (browser-based autonomous mode) is in preview for Pro and above subscribers.

Tags

Serviceskiro
Typeintegration
Conceptsagentic-aiconversational-ai
Use Casesdeveloper-toolsmigration
GeographyGlobal

Related Resources

AI Radar AWS

AWS AI/ML news — curated, researched, explained

An automated intelligence platform that curates, researches, and analyzes AWS AI/ML/GenAI announcements daily. Every report is backed by real research — the system reads linked blog posts and documentation to provide accurate, in-depth analysis.

How Each Report Is Generated

  1. Collection — Daily monitoring of the AWS "What's New" RSS feed
  2. Filtering — AI-powered relevance detection for AI/ML/GenAI topics
  3. Taxonomy Tagging — LLM-based classification across 6 dimensions
  4. Importance Scoring — Point-based system with tag bonuses (1-5 stars)
  5. Research Phase — Follows links to blog posts and documentation
  6. Report Generation — Claude Sonnet produces structured 6-section analysis
  7. Visual Summary — Claude Opus generates Mermaid diagrams for key items
  8. Publishing — Static website rebuilt and deployed via CloudFront

Features

  • Faceted filtering by service, type, concept, and more
  • Multi-dimensional taxonomy with 80+ tags across 6 dimensions
  • Geographic availability badges (Global, APJ, EMEA, AMER) with filtering
  • Timeline visualization of announcement volume
  • PDF export for offline reading
  • Mermaid visual summaries for key announcements
  • Daily automated updates — no manual curation
What makes this different: Each report involves a dedicated research phase where the system reads linked blog posts and AWS documentation pages. This produces analysis that goes beyond the original announcement text.

Technology

Built with Python, AWS Lambda, Amazon Bedrock (Claude Sonnet 4.6, Opus 4.6, Haiku 4.5), S3, CloudFront, WAF, EventBridge, and CDK.

Open Source

This project is open source. Fork it, customize it for your needs, and deploy your own instance.
📦 github.com/bbonik/ai-radar-aws

How Importance Scoring Works

Each announcement receives a point score based on multiple factors. The total score maps to a 1-5 star rating:

1★ < 2 pts 2★ ≥ 2 pts 3★ ≥ 3.5 pts 4★ ≥ 5 pts 5★ ≥ 6.5 pts

Point Breakdown

FactorPointsWhen
Core AI service (Bedrock, AgentCore, SageMaker AI)+4Service named in title
Key AI service (SageMaker, Kiro, QuickSight)+2Service named in title
Other AI-related service+1Default
Blog post link+3Link to aws.amazon.com/blogs/
GitHub samples link+2Link to github.com/aws*
Documentation link+1Link to docs.aws.amazon.com/
New model+1.5Tagged as "new-model"
New service+1Tagged as "new-service"
New feature+0.5Tagged as "new-feature"
Anthropic / OpenAI provider+2Provider explicitly mentioned
Instance / notebook announcement-2Hardware/capacity, not feature
Performance / pricing / security-0.5Incremental updates
Region expansion to APJ+1Expands to Asia Pacific
Region expansion (non-APJ only)-1.5Only expands to other regions

Geographic Relevance Badges

Each announcement card shows a small badge indicating whether the feature is available in your region:

🌐 Global Available in all regions
🌏 APJ Asia Pacific
🌍 EMEA Europe / Middle East / Africa
🌎 AMER Americas (US, Canada, South America)
No badge Geography unknown
How geography is detected: The system detects ALL geographies mentioned in each announcement. If the text mentions specific regions (Tokyo, Frankfurt, Oregon, etc.), the corresponding geography badges are shown. If it says "all regions" or is a new feature with no region specified, it gets the Global badge. Geography is also filterable — click a geo chip to see only announcements available in that region.