Today, we are excited to announce a new integration between Amazon Quick Research and S&P Global. This integration brings both S&P Global Energy news, research and insights and S&P Global Market Intelligence data to Quick Research customers in one deep research agency.
The S&P Global integration expands the capabilities of Quick Research, allowing business professionals to analyze multiple data sources, including global energy news and premium financial intelligence, in one workspace, eliminating the need to switch platforms and turning weeks of research into minutes of focused insight generation. Quick Suite connects information across internal repositories, popular applications, and AWS services to over 1,000 apps through Model Context Protocol (MCP) integration. This agent AI application is reshaping the way we work by transforming how teams find insights, conduct deep investigations, automate tasks, visualize data, and take actions across apps.
This post describes the S&P Global dataset and solution architecture with integration with Quick Research.
Solution overview
S&P Global pioneered two MCP server implementations on AWS. This allows organizations to easily integrate trusted financial services and energy content into AI-powered workflows while maintaining the quality, security, and reliability that business leaders demand.
“Working with AWS expands how S&P Global delivers trusted intelligence through next-generation agent AI experiences. By working with leading AI companies, our goal is to ensure our customers have access to trusted data and insights no matter where their workflows occur.”
– Bhavesh Dayalji, S&P Global Chief AI Officer and Kensho CEO.
S&P Global Energy: Comprehensive commodity and energy intelligence
The S&P Global Energy integration, now available on Amazon Quick Research, leverages the AI Ready Data MCP server to provide comprehensive access to commodity and energy market intelligence across global oil, gas, power, metals, clean energy, agriculture, and shipping sectors. Building on S&P Global's reputation as a trusted market authority, MCP Server uses hundreds of thousands of expert-authored documents, including analysis, commentary, and news articles that reflect decades of industry expertise.
The solution provides a unique multi-horizon perspective, delivering intelligence ranging from daily market updates to one-year outlooks, and extending to over 20 years of scenario analysis. Data is updated every 30 minutes, giving business leaders access to commodity and energy intelligence in near real-time, dramatically accelerating the speed of decision-making when considering regulatory challenges, investment opportunities, and environmental impact.
S&P Global Market Intelligence: Financial Intelligence You Can Trust
The S&P Global Market Intelligence integration now available on Amazon Quick Research uses the Kensho LLM-enabled API MCP server developed by Kensho, S&P Global's AI innovation hub. This MCP server seamlessly integrates with Amazon Quick Research, giving you access to trusted financial data through natural language queries. Financial professionals can access S&P Capital IQ Financials, financial reports, company information, trades, and more just by asking questions.
Kensho solutions address a key challenge in financial services: providing ready access to vast repositories of financial data without the need for complex query languages or technical expertise. Engineering, product, and business teams can save significant time and resources by transforming data extracts that once required hours into conversational queries that return accurate, reliable information in seconds.
solution architecture
S&P Global's MCP server architecture is shown in the following diagram. When you use one of the S&P integrations, traffic flows from Quick Research through Amazon API Gateway to an AWS Application Load Balancer with the MCP service hosted on Amazon Elastic Kubernetes Service (Amazon EKS). MCP servers use data hosted in Amazon S3 and AWS Relational Database Service for PostgreSQL for structured data and Amazon OpenSearch Service for vector storage. This architecture provides an enterprise-ready MCP server with defense-in-depth security, automatic scaling, and comprehensive observability.
MCP is an open standard that supports seamless communication between AI agents and external data sources, tools, and services. MCP works on a client/server architecture. The MCP server handles tool calls, which typically consist of multiple API calls, and exposes business logic implementations as callable functions. This enables AI agents to dynamically discover capabilities, negotiate capabilities, and securely share all the important requirements and context of enterprise-grade applications.
S&P Global's solution has the following key components:
- Automated data pipelines with Amazon Bedrock: At the heart of this solution is a Retrieval Augmented Generation (RAG) data ingestion pipeline using Amazon Bedrock. This pipeline transforms raw market data into AI-enabled data. Documents from S&P Global's own repositories are preprocessed, chunked, and enriched before being converted to vector embeddings using the Bedrock-hosted Cohere Embed model. The ingestion pipeline runs on a schedule and updates the OpenSearch vector store every 30 minutes for near real-time access to energy data.
- Vector and semantic search: Amazon OpenSearch acts as a vector database, storing the embeddings generated by Bedrock and enabling semantic search capabilities across S&P Global's energy data. The OpenSearch vector store is optimized for high-dimensional vector operations and supports fast similarity searches that enhance the MCP server's ability to respond to natural language queries and retrieve context-relevant information.
- Resilience and scale: This solution uses Amazon EKS to host all MCP server solutions on two production clusters that enable traffic splitting and failover functionality. This dual cluster approach provides continuous availability even in the event of unexpected failures. Both cluster autoscaler and horizontal pod autoscaler enable dynamic scaling based on demand. MCP Server is built using the FastMCP framework and provides high-performance HTTP endpoints that comply with the Streamable HTTP Transport specification required by the MCP protocol.
- safety: Security is built into every layer of the solution. API Gateway acts as an endpoint for MCP server access. S&P Global's enterprise identity provider is used for OAuth authentication. API Gateway is further protected by AWS Web Application Firewall (WAF) with advanced threat detection capabilities. AWS IAM roles and policies enforce the principle of least privilege, so each component is given only the permissions it needs. AWS Secrets Manager securely stores credentials for accessing resources and AWS services. AWS security groups and VPC configuration provide network isolation, and TLS 1.2+ with AWS Certificate Manager validates that all data remains encrypted in transit. This layered security includes defense-in-depth security controls.
- Observability: Amazon CloudWatch provides centralized logging, metrics collection, and real-time monitoring of your entire pipeline, from data ingestion to MCP server response. AWS CloudTrail captures detailed API activity logs and audit trails essential for compliance in regulated industries.
conclusion
Built on AWS and integrated with Amazon Quick Research, these MCP servers demonstrate S&P Global's vision for the future of financial services and energy intelligence. That means embracing the transformative potential of AI to make that intelligence more accessible, actionable, and integrated into modern workflows while maintaining the trust, accuracy, and depth that business leaders need.
Ready to get started? Check out Quick Research's third-party data for more information.
About the author
John Aincuff He is a product leader at AWS, based in Seattle, focused on building AI-powered tools that help companies integrate information and accelerate research. He brings over 10 years of experience across digital health, cloud computing, and AI products at Amazon, leading cross-functional teams in product management, engineering, and design to deliver innovative solutions to customers around the world.
Prasanth Ponos is an AWS solutions architect supporting global financial services with over 20 years of industry and technology experience in cloud migration, modernization, and building large-scale distributed systems. His areas of interest are machine learning, containers/Kubernetes, and open source technologies. At AWS, we are part of the machine learning technology community, with a focus on Amazon Bedrock, Amazon SageMaker AI, and Amazon Bedrock AgentCore services.
Brandon Pominville He is a Senior Solutions Architect at AWS based in New York, working with financial services customers around the world to build secure, scalable data and AI platforms on the cloud. With over 20 years of experience across financial services, enterprise data platforms, and cloud computing, he specializes in translating business requirements into technology solutions. Outside of work, Brandon enjoys spending time with his family outdoors and on cruise ships, and playing volleyball.
