AWS Knowledge Base

Integrates with AWS Knowledge Bases to retrieve information using Bedrock Agent Runtime, enabling RAG operations with structured metadata for organizational knowledge access.

The AWS Knowledge Base Retrieval MCP Server enables AI assistants to access information from AWS Knowledge Bases using the Bedrock Agent Runtime. Built with TypeScript, it provides a retrieve_from_aws_kb tool that performs RAG (Retrieval-Augmented Generation) operations, returning both raw context and structured metadata about the sources. The server supports multiple authentication methods including IAM Access Keys and AWS SSO, can be configured with default Knowledge Base IDs, and returns results in a format optimized for AI consumption with separate content items for context and source metadata. This implementation is particularly valuable for organizations that maintain AWS Knowledge Bases and want to incorporate that information into their AI assistant workflows.