Skip to content
Hot eventDeveloping

AWS publishes three tested OAuth patterns for Snowflake Cortex AI on AgentCore

1 reports1 reporting sourcesUpdated 4 h ago

Start here

AI digest

AWS published a technical walkthrough of three OAuth configurations it tested on Amazon Bedrock AgentCore Identity for AI agents calling the Snowflake-managed MCP server, which exposes Snowflake Cortex Agents as a tool type. The patterns are Snowflake OAuth with per-user authorization_code and no external identity provider, three-legged OAuth through corporate SSO, and two-legged OAuth using a shared service user via client_credentials. AgentCore Identity brokers tokens, handling the vault, refresh, and user-to-token binding. All three reference implementations are public and deploy end-to-end through a single deploy.sh script. AWS says the on-behalf-of TOKEN_EXCHANGE grant is generally available on AgentCore Identity but was outside the scope of the three configurations tested. For demonstration, the reference implementations expose SYSTEM_EXECUTE_SQL on the same MCP server as the Cortex Agent; accounts needing both patterns must set a parameter per schema or database so each scope resolves to the right authorization server.

Generated from reports · updated 4 h ago

Report timeline

Follow the reports to see the event from different sides.

November 18
  1. AWS Machine Learning Blog
    Secure OAuth patterns for Snowflake Cortex AI through Amazon Bedrock AgentCore

    AWS tested three OAuth configurations on Amazon Bedrock AgentCore Identity for agents calling the Snowflake-managed MCP server, which exposes Snowflake Cortex Agents as a tool type. The patterns are Snowflake OAuth with per-user authorization_code and no external IdP, three-legged OAuth through corporate SSO, and two-legged OAuth using a shared service user via client_credentials. AgentCore Identity brokers tokens, handling the vault, refresh, and user-to-token binding, and also supports an on-behalf-of TOKEN_EXCHANGE grant.

Heat for this event

Current, comparable range
9
Peak, comparable range
10November 18 05:00
Change in 24 hours
–

The trend compares the same participants over hours observed continuously, so its range can be narrower than the current heat count. Hover or tap the chart for hourly heat; the arrow keys move through it.