MCP server for querying and analyzing AWS Health Events through AI-powered natural language queries
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"chaplin-health-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# Chaplin Health Events MCP Server MCP server for AWS Health Event analysis — AI-powered diagnostics, critical event tracking, and proactive health intelligence across your AWS accounts. > **Powered by [Chaplin](../README.md)** — an agentic AI platform that transforms how organizations understand and respond to AWS health events through natural language queries and real-time analysis. ## Features ### Health Event Intelligence * **Event category breakdown**: Issue, Account Notification, Scheduled Change, Investigation — with event and service counts * **Event type classification**: Configuration Alerts, Cost Impact Events, Maintenance Updates, Migration Requirements, Operational Notifications, Security Compliance * **Critical event tracking**: Upcoming events in 30-day and 30–60 day windows, plus past due events (120 days) * **Drill-down details**: Filter events by service, category, status, region, account, event type, or ARN ### AI-Powered Analysis * **Natural language queries**: Ask questions about your health events in plain English * **Agentic diagnostics**: Same Strands Agent + Bedrock Claude pipeline that powers the Chaplin web dashboard * **Contextual insights**: Impact analysis combining event data with account metadata ### Dashboard Parity Every feature on the Chaplin web dashboard is available as an MCP tool — no browser required. ## Prerequisites 1. **AWS Account** with appropriate permissions 2. **AWS CLI** configured with credentials 3. **Amazon Bedrock**: Access to Claude Sonnet 4 in `us-east-1` 4. **DynamoDB**: `chaplin-health-events` table populated with health event data (see [Chaplin setup](../README.md)) 5. **Python**: 3.10 or higher ## Installation | Kiro | Cursor | VS Code | |------|--------|---------| | [<img src="https://img.shields.io/badge/Add_to_Kiro-blue?logo=data:image/svg+xml;base64,PHN2ZyB3aWR0aD0iMjQiIGhlaWdodD0iMjQiIHZpZXdCb3g9IjAgMCAyNCAyNCIgZmlsbD0ibm9uZSIgeG1sbnM9Imh0dHA6Ly93d3cudzMub3JnLzIwMDAvc3ZnIj48cGF0aCBkPSJNMTIgMk…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.