Show HN: Agentic Identity Broker, OAuth Delegation for AI Agents

Re:Show HN: Agentic Identity Broker, OAuth Delegation for AI... by tiffanyh on Friday November 06, 2026 @12:06PM (#50395079)

Thanks for sharing.

After looking at both GitHub and the .dev website, a few questions:

- why is OAuth delegation not enough?

- is this only for enterprise use cases and if so, why isn't the IT onboarding of an agent not good enough for KYA/KYB? Meaning, if enterprise IT departure trust allowing employees to use an agent, why is anything more needed?

- can you describe more of the actual use cases for this that would happen in the daily life of a user (this last point is what I'm struggling so much with)

Congrats again on your launch.

If your product sites could be more focus on the "why", not the "how" - it'd be tremendously beneficial at least to me (and I presume others).

[ Parent | on HN ]

Re:Show HN: Agentic Identity Broker, OAuth Delegation for AI... by gz5 on Friday November 06, 2026 @12:21PM (#50395325)

not OP but a couple related 'whys' that jumped out to me on their GH so curious your thoughts on them?

>OAuth2 Delegation & Consent. Manage OAuth2 scopes and user consent for third-party service integrations.

>MCP Servers for SaaS. If you want to offer an MCP server to your customers as part of your SaaS, the identity broker can provide an additional consent surface that records which agents were actually used. With centralized tool authorization, you can keep an audit trail of approvals on your side regardless of which agent the customer runs.

[ Parent | on HN ]