Brief
Amazon Bedrock AgentCore adds a consent portal for end-user OAuth with GitHub and Slack targets
Amazon Bedrock AgentCore Identity now offers a Consent portal, a managed web experience and a session binding endpoint for AgentCore Gateway. The accompanying post walks through provisioning a portal, configuring GitHub and Slack authorization code grant targets, and reviewing end-user consent activity in AWS CloudTrail.
The change is a managed consent layer for agents that need end-user OAuth authorization. According to the post, AgentCore Identity now provides a Consent portal, a managed web experience, and a session binding endpoint for AgentCore Gateway.
The walkthrough covers provisioning a portal, configuring GitHub and Slack authorization code grant targets, running the end-user consent flow, and checking activity in AWS CloudTrail. The useful detail is that consent for third-party authorization code grants is managed through a portal and session binding endpoint, with GitHub and Slack as the named targets.
Our reading
The practical weight is in giving agent builders a managed place for end-user consent and session binding, rather than leaving each gateway integration to its own OAuth handling. Teams configuring GitHub or Slack authorization code grant targets should care because the consent flow and its activity in AWS CloudTrail become part of the integration surface.
What to do or watch
The evidenced next step is to walk through provisioning a consent portal, configuring GitHub and Slack authorization code grant targets, running the end-user consent flow, and reviewing activity in AWS CloudTrail.
Source details and supporting facts
Each line is stated by the page named above it.
Stated by aws.amazon.com
- Amazon Bedrock AgentCore Identity now offers a Consent portal.
- Amazon Bedrock AgentCore Identity now offers a managed web experience and session binding endpoint for AgentCore Gateway.
- The post walks through provisioning a portal.
- The post covers configuring GitHub and Slack authorization code grant targets.
- The post covers the end-user consent flow.
- The post shows how to review activity in AWS CloudTrail.
Sources
- AWS Machine Learning BlogText stored 16 September 2026
How this story was checked. Written from the 1 page listed above, stored 16 September 2026; claims checked against that stored text on 16 September 2026.
What that means
- 6 of 6 reported statements were confirmed against the page that carries them; the rest were removed rather than published.
- Figures in the text were required to appear in the stored source text: yes. Identifiers: yes.
- The check reads stored text only: no claim rests on a fresh look that did not happen.
- Where the reporting was silent, the text says so instead of filling the gap.