How is Snowflake Unifying Financial Data With Cortex AI?

AI Data Cloud company Snowflake is introducing Cortex AI for Financial Services, a suite of capabilities aimed at helping financial institutions unify their data ecosystems and deploy AI models.

Alongside this, Snowflake is unveiling a managed Model Context Protocol (MCP) Server.

This is designed to enable firms to connect proprietary data with third-party data from partners such as FactSet, MSCI and The Associated Press.

The MCP Server, now in public preview, allows customers to connect their data with applications and agent platforms, including Anthropic CrewAI and Salesforce’s Agentforce.

This enables firms to build context-rich AI agents while maintaining security and compliance.

“The financial services industry has long been a leader in embracing new technology and AI is no exception. However, the industry faces unique challenges in navigating fragmented data and robust compliance requirements,” says Baris Gultekin, Vice President of AI at Snowflake.

Baris explains that “by bringing AI directly to where their data already lives and enabling secure interoperability with remote agents, Snowflake is making it easier for highly-regulated industries like financial services to power business-critical use cases.”

The role of standardising AI agent and data integration

The MCP Server addresses a significant challenge in connecting AI agents to enterprise systems.

Previously, teams often needed customised solutions for each integration a process that could slow AI adoption.

The MCP provides a standardised method for large language models (LLMs) to integrate with data APIs and services.

It connects Cortex Analyst and Cortex Search to external AI agents through a standards-based interface, unifying structured and unstructured data retrieval.

This approach could eliminate the need for custom integrations and accelerate the delivery of AI applications – and the server can connect with a range of platforms, including Anthropic, Amazon Bedrock, CrewAI Mistral and Salesforce's Agentforce.

The importance of powering enterprise AI from pilots to production

This move towards standardisation is seen as a crucial step in maturing enterprise AI.

“Enterprises are moving from AI pilots to production, but until now, securely connecting AI to proprietary data has been a critical barrier,” says Jonathan Pelosi, Head of Industry Financial Services at Anthropic.

He explains the partnership uses MCP to connect governed data directly to their model Claude allowing customers to turn proprietary data into a competitive advantage.

Platform providers also see the development as enabling deeper integration.

Gary Lerhaupt, Vice President of Product Architecture at Salesforce, says it will “enable deeper cross-platform connectivity and power more intelligent agentic experiences within Agentforce” accelerating AI agent deployment.

The shift towards complex multi-agent systems is a key factor.

João Moura, CEO of CrewA,I notes that these systems require secure access to enterprise data at scale.

He adds that the MCP Server "provides the essential secure pipeline for our agent crews to access, analyse and act upon governed data.”

How to enable multi-agent architectures with secure data

Financial services firms are already using these capabilities.

Ian Macomber, Head of Analytics at Ramp, describes how his company processes thousands of pieces of customer feedback to understand their needs.

“With Snowflake Cortex AI we can securely tap into and analyse our unstructured customer data, allowing teams across Ramp to ask questions in plain English and get instant answers,” Ian explains.

He says Snowflake makes it easy to democratise data-driven decision-making, which enables Ramp to innovate faster and build the best platform for its customers.