AI Meets Digital ID: Credential Issuance and Verification using MCP [Live Demo]

AI agents are quickly moving from experimentation to real-world deployment, but one critical question remains: how do you establish trust when agents start acting on behalf of users?

In a recent webinar, Mike Parkhill (Head of Engineering at Dock Labs) and Agne Caunt (Product Owner at Dock Labs) explored this challenge and demonstrated how identity infrastructure can play a central role in solving it.

The session focused on Truvera’s MCP (Model Context Protocol) server, showing how agents can issue, verify, and eventually hold digital ID credentials, and how this enables more secure, auditable, and constrained agent behavior. Along the way, they walked through a live demo of credential issuance and verification, and shared their perspective on where agent identity, delegation, and agentic commerce are heading next.

(01:08) Why agent identity is becoming a problem

(02:20) What MCP (Model Context Protocol) is

(03:19) Goal: identity infrastructure for AI agents

(04:27) What MCP enables for agents (analogy + capabilities)

(05:56) Demo setup (Claude + web wallet)

(14:27) Roadmap: wallet MCP and agent capabilities

(15:16) Agent-to-agent (A2A) and DIDComm direction

(16:13) Introduction to Agentic Payment Protocol (AP2)

(18:02) AP2 mandates (cart, intent, payment) explained

(19:51) Demo: issuing a cart mandate to an agent wallet

(21:31) End of demo and transition to Q&A

(22:21) What is an agent’s identity?

(25:05) How MCP improves security and limits agent scope

(28:07) Schema flexibility and support for new protocols

(30:03) Ease of implementation and setup

(31:43) How agents get their identity (onboarding)

(33:04) Human-to-agent delegation model

(34:19) EUDI and business wallet discussion

(40:38) What happens when an agent invokes MCP tools

(42:52) Multi-tenant vs one-to-one MCP architecture

(45:36) Why did:cheqd was chosen

(47:41) Real-world use cases (e-commerce, travel)

(49:01) Sensitive use cases (loans, insurance, documents)

(50:23) DID methods (did:key vs cheqd) explained

(52:45) Closing remarks and next steps

📚 EXPLORE:

Website - https://www.dock.io/

👨‍👩‍👧‍👧 FOLLOW:

LinkedIn - https://www.linkedin.com/company/docknetwork/

Denne episoden er hentet fra en åpen RSS-feed og er ikke publisert av Podme. Den kan derfor inneholde annonser.

Episoder(75)

Building a Business Model Around EUDI Credentials [Live]

In this session, we look at how money will move in the European Digital Identity ecosystem. EUDI is designed so that people hold verified credentials in their own wallets and share them with consent, ...

5 Okt 1h 6min

How to Give AI Agents Verifiable Proof of Authority [Live Demo]

In this session, we show how an AI agent can be given a narrow, revocable slice of a person's authority, and how the counterparty on the other side of the transaction can verify it. Identifying an age...

14 Sep 56min

FIDO’s Vision for Passkeys, Digital Identity and AI Agents, with Andrew Shikiar (FIDO Alliance CEO)

In this session, Andrew Shikiar, CEO at the FIDO Alliance, explains why passkeys succeeded where earlier password replacements failed, and how the FIDO Alliance is now applying the same playbook to di...

3 Aug 58min

The Identity Challenge in AI Agent Payments (with Harsh Mehta from Worldpay)

In this session, Harsh Mehta of Worldpay and Dock Labs unpack the identity and trust challenges behind AI agents and agentic payments: what is genuinely working today, what is still marketing, and wha...

20 Jul 44min

The EU Digital Identity Wallet: A Practical Guide

In this session, Agne Caunt and Richard Esplin from Dock Labs break down the EU Digital Identity Wallet (EUDI) at the level most explainers skip: how the ecosystem is actually structured, what matters...

13 Jul 1h 14min

Liability in Agentic Commerce: Who Takes the Risk? [Live]

What happens to liability when the entity making a purchase is not a human? AI agents are moving from research into commercial reality. They can research and execute purchases. But the legal, identity...

15 Jun 58min

Can We Really Have Zero Trust with a Federated Identity Architecture? With Justin Richer (MongoDB)

Most organizations say they are doing Zero Trust. Many still trust their IAM directory implicitly, protect it with a firewall, and call that a modern identity architecture. That is a perimeter by anot...

1 Jun 1h

Trusted Caller Identity: Pilot Results from GSMA & Telefónica [Live]

This session presents the results of a six-month proof of concept run by Telefónica Tech, GSMA, Dock Labs, and TMT ID to rebuild call center authentication using mobile network APIs and verifiable cre...

18 Mai 59min