Model Context Protocol (MCP) integration in Amazon Quick transforms how financial analysts access time-series market intelligence, removing the need for complex database queries. As a financial analyst, you navigate millions of stock trades flowing through markets every second, searching for patterns that drive trading decisions. Financial institutions often use time series databases to analyze high-frequency market data.

In this post, we walk through a practical implementation using KDB-X MCP server integration with Amazon Quick, demonstrating how traders and analysts can ask questions using conversational language and receive actionable insights from datasets. You can apply this same integration pattern across various domains, from financial market analysis to IoT sensor monitoring to DevOps performance dashboards, where you need to simplify access to time series insights.

Amazon Quick is a comprehensive, generative AI-powered business intelligence service that you can use to analyze data, create visualizations, automate workflows, and collaborate across your organization. With MCP integration in Amazon Quick, you can connect to MCP servers for both task execution and data access capabilities. MCP provides a standardized way to connect AI systems with external tools and data sources. In this example, you’ll work with time series databases provided by KDB-X, which is built on the industry-leading kdb+. kdb+ is a high-performance time-series database and analytics engine, powered by the vector language q.

We begin by installing the KDB-X MCP server on an Amazon Elastic Compute Cloud (Amazon EC2) instance. This installation enables the KDB-X service to run continuously and establishes the connection between the MCP server and KDB-X service for query execution. Quick translates natural language queries into SQL statements and passes them to the KDB-X MCP server, which executes these queries against the KDB-X database.

To connect the MCP server with Quick, we use Amazon Bedrock AgentCore Gateway as an authentication and routing layer. The AgentCore Gateway serves as a single access point for the agent to interact with its tools. In our architecture, we configure MCP servers as targets within the AgentCore Gateway, enabling communication with the MCP server running on Amazon EC2. We also implement inbound authorization for the AgentCore Gateway, which validates users attempting to access targets through the gateway. Since MCP integration in Quick requires authentication credentials, the inbound authentication to the gateway fulfills this requirement for the MCP connector. For this solution, we configure Amazon Cognito as the identity provider for accessing the AgentCore Gateway. This integration appears in the Quick chat interface as actions, allowing users to perform relevant tasks and boosting productivity through third-party service integration.

Verify that you meet the following prerequisites to deploy the solution in your own AWS account using the step-by-step instructions in this post. Before you begin, make sure that you have the following: