The Future of MCP — David Soria Parra, Anthropic

AI Engineer · Beginner ·🤖 AI Agents & Automation ·3w ago

Skills: Agent Foundations80%AI Systems Design70%

In this Keynote, I will lay out what I believe will be true for agents in 2026 and how MCP plays a part in this. Let's take a look what connectivity for agents might look like. Speaker info: - https://x.com/dsp_ - https://www.linkedin.com/in/david-soria-parra-4a78b3a/ - https://github.com/dsp Timestamps 0:00 Introduction and the vision for MCP applications 1:34 Looking back at the evolution of the MCP ecosystem over the last 18 months 2:30 Ecosystem growth and adoption milestones 3:46 Moving from exploration in 2025 to production in 2026 5:07 The 2026 connectivity stack: Skills, MCP, and CLI/Computer use 7:47 Improving client harnesses: Progressive Discovery 9:39 Programmatic tool calling and agent orchestration 12:00 Best practices for designing agents and server authors 13:42 Future roadmap for the MCP protocol and core improvements 15:23 Strategic integrations and enterprise features 16:32 Upcoming extension mechanisms and skills over MCP 17:15 Conclusion and call for community feedback

Watch on YouTube ↗ (saves to browser)

Sign in to unlock AI tutor explanation · ⚡30

More on: Agent Foundations

View skill →

Build and Deploy an Agent with Reasoning Engine in Vertex AI

Adding a Phone Gateway to a Virtual Agent

From Zero to Working AI Agent in 60 Seconds

From Zero to Working AI Agent in 60 Seconds

Create An AI Agent With Replit That Automates Your Sales

Create An AI Agent With Replit That Automates Your Sales

Capstone: Autonomous Runway Detection for IoT

Capstone: Autonomous Runway Detection for IoT

AI Agents with Model Context Protocol & Typescript

AI Agents with Model Context Protocol & Typescript

Related AI Lessons

Getting Started With Agent-to-Agent aka A2A Protocol

Learn how the Agent-to-Agent (A2A) protocol enables coordinated work among isolated AI agents and its importance for AI engineers

Getting Started With Agent-to-Agent aka A2A Protocol

Learn how Agent-to-Agent (A2A) protocol enables coordinated AI workforces and its importance for AI engineers

Medium · Python

Getting Started With Agent-to-Agent aka A2A Protocol

Learn about the Agent-to-Agent (A2A) protocol, which enables coordinated workforce among isolated AI agents, and its importance for AI engineers

One MCP Server or Ten? The Architecture Decision That Can Make or Break Your AI Agent

Learn how to architect your AI agent's infrastructure to ensure scalability and reliability, a crucial decision for e-commerce applications

Medium · Python

Chapters (12)

Introduction and the vision for MCP applications

1:34 Looking back at the evolution of the MCP ecosystem over the last 18 months

2:30 Ecosystem growth and adoption milestones

3:46 Moving from exploration in 2025 to production in 2026

5:07 The 2026 connectivity stack: Skills, MCP, and CLI/Computer use

7:47 Improving client harnesses: Progressive Discovery

9:39 Programmatic tool calling and agent orchestration

12:00 Best practices for designing agents and server authors

13:42 Future roadmap for the MCP protocol and core improvements

15:23 Strategic integrations and enterprise features

16:32 Upcoming extension mechanisms and skills over MCP

17:15 Conclusion and call for community feedback

Build & Automate ANYTHING With Hermes Agent

Julian Goldie SEO