# Amazon — Govern AI agent access with Okta Cross App Access and Amazon Bedrock AgentCore – Part 2

- Company: Amazon (amazon.com)
- Announced: 2026-11-06T17:09:23+00:00
- Category: not stated
- Coverage: not counted
- Announcement: no
- Group: routine
- Source: https://aws.amazon.com/blogs/machine-learning/govern-ai-agent-access-with-okta-cross-app-access-and-amazon-bedrock-agentcore-part-2/
- Record: https://forck.live/items/32595-govern-ai-agent-access-with-okta-cross-app-access-and-amazon-bedrock-agentcore
- Subject: Bedrock / Nova
- Pricing: The EKS control plane costs $0.10 per hour, plus nodes and the Amazon EKS Auto Mode management fee

AWS's second post in a series shows how to move a working Okta Cross App Access agent setup from a single agent and two MCP servers to a topology that holds hundreds of agents and thousands of tools. The first post proved the governance mechanism, where Okta decided which agent could act for which user and Amazon Bedrock AgentCore Identity redeemed that grant inside the agent on Amazon Bedrock AgentCore runtime. Amazon Bedrock AgentCore Gateway becomes the single front door and redeems Okta's grant for each target, while Policy in Amazon Bedrock AgentCore evaluates Cedar policies that bind each tool to the agent and the scope Okta delegated. A second reporting agent on Amazon Elastic Kubernetes Service joins under its own Okta identity, showing the front door does not care where an agent runs. Amazon Bedrock AgentCore Observability with Amazon CloudWatch gives one place to read every decision, including Okta's, which streams its System Log through Amazon EventBridge. AWS says the additions take about 90 minutes and that the EKS control plane costs $0.10 per hour, plus nodes and the Auto Mode management fee.

## Evidence

Verbatim from https://aws.amazon.com/blogs/machine-learning/govern-ai-agent-access-with-okta-cross-app-access-and-amazon-bedrock-agentcore-part-2/:

> In Part 1 , you built a task agent on Amazon Bedrock AgentCore , a platform to build, connect, and optimize agents at scale, with any framework or model. The agent runs on Amazon Bedrock AgentCore runtime, a capability of Amazon Bedrock AgentCore, and acts for signed-in users through Okta Cross App Access (XAA). Okta decided which agent might act for which user, and Amazon Bedrock AgentCore Identity, a capability of Amazon Bedrock AgentCore, redeemed Okta’s grant inside the agent. That proves the governance mechanism, and it runs on a deliberately small topology: one agent, two Model Context Protocol (MCP) servers, and the authorization check written into each server.
> 
> The mechanism scales. The topology doesn’t. Three things that are fine for one agent and two tools become the work in an enterprise with hundreds of agents and thousands of tools:
> 
> In this post, you make that change on the Part 1 solution. Amazon Bedrock AgentCore Gateway, a capability of Amazon Bedrock AgentCore, becomes the single front door and redeems Okta’s grant for each target. Policy in Amazon Bedrock AgentCore evaluates Cedar policies that bind each tool to the agent and the scope Okta delegated.

---

Record: https://forck.live/items/32595-govern-ai-agent-access-with-okta-cross-app-access-and-amazon-bedrock-agentcore
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md
