Snowflake Cortex Agents + MCP: Exposing agents to external AI clients via Snowflake MCP

Enterprise AI agents are powerful but data-blind. Teams building with Claude, Cursor, or custom agents hit the same wall: their AI can reason, but it can't securely reach governed enterprise data without someone writing a custom integration, moving data out of Snowflake, or punching holes in security policy. The result is either a fragile bespoke connector that the data team owns forever, or agents that hallucinate because they're working off stale exports. The Model Context Protocol (MCP) has rapidly become the default standard for connecting AI clients to external tools. Every major AI IDE (Cursor, Windsurf), every frontier model host (Claude, OpenAI), and a growing list of enterprise agent frameworks already speak MCP natively. Snowflake's managed MCP server meets customers exactly where that wave is breaking: one configuration, no infrastructure, and every tool call flows through OAuth + RBAC-governed access. This lab is built for data and AI teams at companies already on Snowflake who are actively exploring or piloting AI agents. If your customer has said "we're using Claude" or "our engineers are in Cursor all day", this is the exact session to put in front of them.

Snowflake's managed MCP server acts as a governed AI gateway: it exposes Cortex Analyst, Cortex Search, and direct SQL execution as callable tools, then handles authentication, tool discovery, and invocation entirely within Snowflake. External AI clients connect via OAuth and see only the tools and data their role permits. No data leaves Snowflake, no custom middleware runs, and every query drives warehouse consumption the customer is already paying for. We'll build both sides of this story from scratch: structured revenue data queried through a semantic view via Cortex Analyst, and unstructured sales call transcripts retrieved via Cortex Search and then unify both behind a single MCP server and watch a real AI client answer questions that span both.

Set the stage (15 min): Walk through the MCP standard, where Snowflake's managed server fits, and what we're building today Build the data layer (25 min): Load a sample dataset (revenue metrics + sales call transcripts), create a semantic view over the structured data, and stand up a Cortex Search service over the unstructured data Configure the MCP server (15 min): Create and configure a Snowflake-managed MCP server, expose Cortex Analyst and Cortex Search as tools, and set OAuth scopes and RBAC policies governing tool access Connect the AI client (15 min): Wire Claude Desktop (or Cursor) to the MCP server using the OAuth flow, verify tool discovery, and confirm the client can see only what it's permitted to Run live queries end to end (15 min): Ask multi-hop questions that require the agent to combine structured revenue data and unstructured transcript context; observe how the client picks the right tool, constructs the right query, and returns grounded answers Wrap-up + expansion patterns (5 min): Discuss adding custom tools, chaining agents, and how this pattern scales to a full enterprise AI layer

By the end of this lab, you will have built and run a production-realistic AI data access pattern entirely inside Snowflake. You'll know how to model data for agent consumption with semantic views, how to make unstructured content retrievable with Cortex Search, and how to wire both into a managed MCP server that any MCP-compatible AI client can call. You'll understand the OAuth and RBAC controls that let you govern exactly what an agent can see and do.