← back
A2A & MCP Workshop: Automating Business Processes with LLMs — Damien Murphy, Bench
Original: A2A & MCP Workshop: Automating Business Processes with LLMs — Damien Murphy, Bench
Takeaway
A2A handles remote agent-to-agent discovery while MCP handles tool/context plumbing — pick them only when you don't control both sides.
Summary
- Workshop builds a multi-agent system using Google's A2A protocol for cross-org agent discovery plus MCP for tools/context, triggered by webhook.
- A2A enables agent specialization (100 agents doing one thing) and remote service discovery; MCP is the 'USB-C' standard with ~10k tools (7k via Zapier MCP).
- Guidance: don't use A2A/MCP when you own both ends — local function calls are faster, easier to debug; use them for third-party tools and unknown remote agents.
- Discusses MCP sampling (server uses host LLM), prompt caching, and context management for autonomous workflows; speaker works at Bench Computing building a 'better Manus'.
mcpa2aagents
Original description
Ever wished your webhooks could think for themselves? Join us to discover how A2A agents can transform passive webhook endpoints into intelligent workflow processors. In this session, we'll show you how to build a system that automatically spawns AI Agents to handle incoming webhooks. Using Google's Agent-to-Agent framework and MCP, you'll learn how to create dynamic AI agents that respond to events, communicate with external services, and make decisions based on content analysis. See the future of workflow automation where webhooks don't just trigger actions—they trigger intelligence! About Damien Murphy Full Stack Dev for 20+ years focusing on AI Agents Recorded at the AI Engineer World's Fair in San Francisco. Stay up to date on our upcoming events and content by joining our newsletter here: https://www.ai.engineer/newsletter