AWS open-sources Chaplin: self-service AWS Health analytics on Amazon Bedrock agents

AWS released an open source project Chaplin — a tool for self-service analytics of AWS Health events using AI-agents based on Amazon Bedrock and Model Context Protocol.

What is Chaplin

Chaplin stands for Customer Health and Planned Lifecycle Intelligence Nexus. It's not another paid AWS service, but an open toolkit that teams can deploy themselves, adapt to their own stack, and extend for specific tasks. At the core of the solution are AI-agents integrated with the AWS Health API through MCP (Model Context Protocol). The agents can parse structured AWS events — notifications about outages, planned maintenance, resource lifecycle changes — and transform them into specific conclusions in natural language. Getting a summary of active incidents is now possible not through the AWS Console, but through a simple chat interface.

How MCP Architecture Works

MCP is an open standard for interaction between LLM applications and external tools. Anthropic promotes it, and major players — from Microsoft to Google — are actively adopting it. In Chaplin, Amazon Bedrock agents connect to AWS Health tools through an MCP server, which provides a flexible extension point without rewriting the core. Through this architecture, agents can:

• Query the status of specific resources — EC2, RDS, Lambda and other services
• Filter events by region, account, or service type
• Build a timeline of incidents and planned technical changes
• Generate summaries for non-technical stakeholders without jargon
• Recommend next steps based on event type and priority

Any team member — product manager, SRE, financial analyst — can ask a question in natural language and receive a structured answer without understanding the console or writing SQL.

Why Teams Need This

AWS Health generates a constant stream of notifications: planned maintenance windows, deprecation warnings, regional incidents, limit changes. Previously, navigating this stream required manual work through dashboards or specialized tools that demanded specific skills. Chaplin transitions this process to self-service mode. Now teams can:

• Get a summary of all active events across their infrastructure in seconds
• Learn which resources will be affected by upcoming planned maintenance
• Assess the impact of an incident on a specific workload or business process
• Automatically notify the right people through a chosen channel

Since Chaplin is published as open source, organizations can adapt it: add their own data sources, change agent logic, or integrate with internal monitoring and ticketing systems.

Amazon Bedrock as the Foundation

AWS uses Amazon Bedrock for agents — its own platform for working with LLMs from leading providers: Anthropic, Meta, Mistral, AI21 and others. This provides flexibility in choosing a model for specific requirements in terms of cost, speed, and answer quality. The combination of Bedrock and MCP is an emerging pattern in the AWS ecosystem for enterprise AI: not just a chatbot, but an agent with real access to live infrastructure data that can not only respond but also initiate requests to external systems.

What This Means

Chaplin is a prime example of how MCP ceases to be an academic standard and becomes a real production architecture. AWS uses it not in a demo, but in a solution for working with critical infrastructure state data. Companies that want to reduce response time to infrastructure events and decrease the load on DevOps teams should study this tool.

*Meta is recognized as an extremist organization and banned in the Russian Federation.