Apono Agent Privilege Guard for AWS
Configure governed, just-in-time AI access to AWS resources
Set up Apono Agent Privilege Guard for AWS to give AI agents controlled, temporary access to AWS resources.
An Apono admin configures the AWS integration, an agentic access flow, and the AWS MCP. Each user then connects a supported AI client through the Local Agentic Gateway, which brokers requests between the AI client, Apono, and AWS.
Set up the Apono account
An Apono admin completes this setup once.
After the Apono account setup is complete, each user can connect a supported AI client to the Agentic Gateway.
Prerequisites
AWS Organization integration
Connected Apono integration
Verify the integration exists and is healthy on the Connected tab. If no AWS Organization integration is connected, follow the AWS integration docs.
Full-Access connector
Required connector permissions
The connector used by the AWS Organization integration must be deployed with Full-Access (Manage IAM) permissions. See the Apono Connector for AWS docs.
Create an agentic access flow
Create a Self Serve access flow that allows agents to request temporary access to AWS resources on behalf of permitted users:
Follow the procedure in Self Serve Access Flows to define the requestors, resources, access duration, and approval process. As you create the flow, apply the following settings for agentic access.
Access Flow Name
Enter a unique, user-friendly name, such as Agentic - AWS.
When Requestor
Select the users or groups on whose behalf an agent can request access. The agent can request access only on behalf of its associated user, so that user must match these requester conditions. For Can request for, select Themselves.
Request access to
Select your AWS Organization integration, and then select the resource types, resources, and permissions the agent can access.
Follow the Integrations instructions in the Define the resource section of the Self Serve Access Flows guide.
Grant for
Set the access duration to 5 minutes.
Approval
Select Automatic
Settings
Click the Restrict to agentic access toggle to enable the setting.
Allow Extend Duration does not apply to agentic access flows. When access expires, the agent requests access again.
Configure any other Self Serve access flow settings according to your organization’s access policies.
Click Save Access Flow.
Enable MCP features and the AWS MCP
Follow these steps:
On the Account Settings page, under AI & Automation, click the Enable MCP features toggle to enable the setting. The toggle turns green.
On the MCPs tab, under Apono Managed Tools, click the toggle on the AWS MCP card to enable the tool.
Learn more about Model Context Protocol servers.
After setup, use the AI Agents tab to view discovered agents and their associated users. Use the AI Sessions tab to review agent activity, including access grants, tool calls, and intent policy decisions.
Set up the Agentic Gateway on a local machine
Each user running the gateway completes this setup on their local machine.
Prerequisites
Apono account setup completed
Enablement of MCP feature for the Apono account
Confirm that an Apono admin has set up the Apono Account:
Connected the applicable integration
Created an agentic access flow with Restrict to agentic access enabled
Enabled MCP features and the AWS MCP
macOS
Supported operating system
The Local Agentic Gateway is currently supported on macOS.
Node.js 20+
Required runtime
The gateway is launched with npx, which runs @apono-io/apono-mcp@latest, downloads the gateway binary, and manages the Apono sign-in. No separate Apono CLI installation is required.
uv
Required by the AWS MCP Install it per the uv installation docs.
Python 3.13
Required by the AWS MCP
Install with uv: uv python install 3.13
Configure your AI client
If the Agentic Gateway is already configured for this client, skip to Verify your agent.
Follow these steps:
Run the following command. If this is the first run, a separate browser tab opens.
(First run only) Log in to Apono in the open browser tab.
Follow these steps:
In Claude, from the main navigation, click Claude > Settings > Developer. The Settings page appears.
Click Edit Config. The claude_desktop_config.json file opens.
Add the following configuration.
Save the file.
Quit and restart Claude desktop.
(First run only) Log in to Apono in the browser tab that opens.
Follow these steps:
In Cursor, from the main navigation, click Tools & MCPs. The Tools page appears.
Under Home MCP Servers, click New MCP Server. The mcp.json file opens.
Add the following configuration.
Save the file.
Quit and restart Cursor.
(First run only) Log in to Apono in the browser tab that opens.
Verify your agent
Perform the following tests:
Ask the assistant to list your available integrations. The AWS target should appear.
Ask it to perform an action, such as "Request access to account X and list its S3 buckets". The agent will request access through the agentic access flow.
Apono handles AWS authentication for you: once the request is approved, it fetches short-lived AWS credentials and wires up the connection automatically. The call should return live AWS data.
If either task fails, troubleshoot your setup.
Troubleshooting
Apono Account
Access is granted, but AWS grants fail.
The connector backing the AWS Organization integration is likely still Read-Only (Discovery). The integration must be Full-Access (Manage IAM).
See the Full-Access connector prerequisite above and the Apono Connector for AWS docs.
Local Machine
No targets or integrations are listed.
Follow these steps:
Reauthenticate to Apono.
Fully restart the AI client so the updated credentials take effect.
If the target is still unavailable, confirm with an Apono admin that the platform setup is complete. This includes the integration, agentic access flow, MCP feature enablement, and applicable Apono Managed MCP.
Follow the troubleshooting instructions in the applicable platform setup guide.
Last updated
Was this helpful?