WeAreDevelopers Logo WeAreDevelopers
Sign in
For You LIVE
World Congress 2026 Europe • Jul 10, 2026 • Session details

API, MCP or MCP App? Choosing the right surface for AI agents

Rishabh Budhiraja , Rishi Deorukhkar

Are standard APIs enough when your end user is an AI? Learn how the Model Context Protocol shifts agency directly to the model through dynamic apps.

Pause
Mute Enter Fullscreen
#1 about 3 min

Core concepts and advantages of the Model Context Protocol

How MCP shifts agency from developers to models by enabling dynamic API discovery and structured tool calls.

#2 about 3 min

Architectural overview of the trial Edialo MCP implementation

Offering rich e-commerce search capabilities through trial MCP tools like product history mapping and custom integrations.

#3 about 3 min

Securing connections using dynamic client registration and metadata

Managing secure AI agent access through client metadata documentation rather than decentralized per-server registration.

#4 about 4 min

Evolving AI responses from text walls to interactive interfaces

The transition from text-only output to embedded interactive UI widgets for richer product exploration.

#5 about 4 min

Managing context and interaction state in sandboxed widget frames

How sandboxed MCP user interface elements synchronize client interaction state back to the model context.

#6 about 2 min

Managing cross-platform deployment complexities for AI agent applications

Using unified frameworks to abstract API differences between separate provider capabilities and simplify cross-platform deployment.

#7 about 3 min

Optimizing semantic tool descriptions for reliable model invocation

Crafting precise documentation prompts to control how and when large language models select available functional tools.

#8 about 2 min

Integrating user interfaces and holistic journeys into agent context

Shifting application design to treat frontend interactions as continuous contextual inputs for agent-driven task completion.

#9 about 5 min

Running automated evaluation tests for conversational tool selection

Validating AI component reliability and prompt effectiveness against explicit test conditions using open-source evaluation runners.

#10 about 2 min

Visualizing the future of proactive multi-tool agent orchestration

Exploring capabilities where language models seamlessly string together multiple personalized applications to solve complex user tasks.

#11 about 5 min

Q&A on platform discovery, security, and prompt injection

Resolving challenges related to AI engine optimization, protecting endpoints from malicious payloads, and tracking framework updates.

Matching moments

1:49 min

Introduction to MCP apps and dynamic UI elements

Vishal Dodiya Vishal Dodiya · Europe 2026 Virtual

2:21 min

Integrating Model Context Protocol for non-technical users

Jordan Tigani Jordan Tigani · World Congress 2026 Europe

5:54 min

Standardizing agent interactions with the Web MCP proposal

Chris Heilmann Chris Heilmann +2 · LIVE

1:11 min

Treating AI tools as standard governed enterprise capabilities

Stefan Mesquita Stefan Mesquita · World Congress 2026 Europe

1:44 min

Summarizing developer experience and artificial intelligence companions

Robert Hoffmann Robert Hoffmann +1 · LIVE

2:21 min

Applying context engineering across the full software lifecycle

Neel Sundaresan Neel Sundaresan +1 · World Congress 2026 Europe

More from World Congress 2026 Europe

Building the Nervous System of AI - Michael Kagan (NVIDIA) thumbnail
29:17
3 months ago

Building the Nervous System of AI - Michael Kagan (NVIDIA)

Michael Kagan, Sead Ahmetović

Five Things in Tech that Matter Now - WeAreDevelopers World Congress 2026 Closing Keynote thumbnail
19:41
3 months ago

Five Things in Tech that Matter Now - WeAreDevelopers World Congress 2026 Closing Keynote

Christian Heilmann

The Sound of Your Secrets: Teaching Your Model to Spy, So You Can Learn to Defend thumbnail
32:06
3 months ago

The Sound of Your Secrets: Teaching Your Model to Spy, So You Can Learn to Defend

David vonThenen

Super scaling for the Super Bowl: How to survive 30 million users hitting your backend in 30 minutes thumbnail
35:13
3 months ago

Super scaling for the Super Bowl: How to survive 30 million users hitting your backend in 30 minutes

Irina Branovic

Running Secure Life Science Research at Scale using Hybrid GPU HPC and Kubernetes 🧬 thumbnail
24:23
3 months ago

Running Secure Life Science Research at Scale using Hybrid GPU HPC and Kubernetes 🧬

Jeremy Murray

Angstfreude - AI and Corporate Culture - The Thrill and the Threat thumbnail
30:26
3 months ago

Angstfreude - AI and Corporate Culture - The Thrill and the Threat

Axel Ebert, Karin Krobath

Related videos

Building APIs for Agents vs Systems. Is MCP the answer? thumbnail
27:52
World Congress 2026 Europe • 3 months ago

Building APIs for Agents vs Systems. Is MCP the answer?

Adam Bird

Beyond Prompting: Building Scalable AI with Multi-Agent Systems and MCP thumbnail
25:32
World Congress 2025 • about 1 year ago

Beyond Prompting: Building Scalable AI with Multi-Agent Systems and MCP

Viktoria Semaan

MCP Mashups: How AI Agents are Reviving the Programmable Web thumbnail
23:17
World Congress 2025 • about 1 year ago

MCP Mashups: How AI Agents are Reviving the Programmable Web

Angie Jones

From Zero to MCP UI Hero: Building Context-Aware AI Apps That Actually Work thumbnail
20:59
Europe 2026 Virtual • 3 months ago

From Zero to MCP UI Hero: Building Context-Aware AI Apps That Actually Work

Vishal Dodiya

MCP doesn’t suck — your agent does thumbnail
27:55
World Congress 2026 Europe • 3 months ago

MCP doesn’t suck — your agent does

Jan Curn

From APIs to MCP: Enterprise Governance, Registry, and Controls thumbnail
22:30
World Congress 2026 Europe • 3 months ago

From APIs to MCP: Enterprise Governance, Registry, and Controls

Stefan Mesquita

Related articles

From learning to earning

Jobs that call for the skills explored in this talk.