Anup Jadhav
Anup Jadhav
Blog, newsletter, projects and more
⌘K
Subscribe Sign in
Anup Jadhav
AI Agents

MCP + A2A: The Protocols Making AI Agents Actually Work Together

Anup Jadhav

by Anup Jadhav

MCP + A2A: The Protocols Making AI Agents Actually Work Together

I presented this at the AI Engineer meetup in London. It is a short, practical overview of why agent interoperability matters now, and how two protocols, MCP & A2A, make it workable today.

Why watch

A crisp mental model you can share with your team. It shows the problem, places MCP and A2A in the stack, and walks through a concrete hiring workflow so you can map it to your own systems.

What you will learn

  • Where MCP fits: tools, resources, prompts, sampling, and common transports
  • Where A2A fits: agent cards, tasks, messages, artifacts
  • Three architectures for recruitment automation and why MCP plus A2A scales
  • How to cut N squared glue work by standardising layers

Talk context

Delivered live to practitioners at the AI Engineer meetup. The goal was to give teams a shared language for splitting access (MCP) from collaboration (A2A) so projects stop stalling on bespoke integrations.

Who this is for

Engineers and architects shipping agent systems in production. If you are tired of bespoke glue, this will help you line things up.

Subscribe

If this was useful, subscribe to the newsletter (and the new youtube channel) for deeper implementation notes, patterns, and code examples.

Subscribe to The AI Engineering Brief

No spam, no sharing to third party. Only you and me.

More like this

Rethinking RAG: Meta’s REFRAG

Rethinking RAG: Meta’s REFRAG

For the past few years, retrieval-augmented generation (RAG) has been the workhorse architecture for grounded LLM applications. You retrieve relevant

Prompt Engineering vs Context Engineering

From Anthropic: https://www.anthropic.com/engineering/effective-context-engineering-for-ai-agents Prompt Engineering: Prompt engineering refers to methods for writing and organizing LLM

AI agents are starting to do real work

Ethan Mollick argues that AIs have quietly crossed a line. OpenAI recently tested models on complex, expert-designed tasks that usually
Cargo Cult Vibe Coding

Cargo Cult Vibe Coding

In the age of AI code generation, we risk trading craftsmanship for ritual It's the 1940s in the
The Rubber Duck That Talks Back

The Rubber Duck That Talks Back

How AI is Teaching Developers to Think Before They Code
Why Your AI Agents Keep Breaking (And How Systems Thinking Can Fix Them)

Why Your AI Agents Keep Breaking (And How Systems Thinking Can Fix Them)

Most teams build AI like traditional software. That's the problem.