MCP: The Good, The Bad & The Overhyped
Every legal AI vendor is talking about MCP. Far fewer explain what it actually does, or where the security gaps sit. Join Pieter Buteneers, Co-Founder and CTO of Emma Legal, on 17 September for a plain-language session on what MCP opens up, what it doesn't, and where it earns its place in legal due diligence.
What you'll walk away with
MCP (Model Context Protocol) lets an AI model reach into live systems: a data room, a document store, a CRM. Not a copy of the data. The real thing.
That is genuinely useful, and it is also exactly where the risk sits.
Pieter has been building on MCP since it landed. In this session he takes it apart in plain language: what it does well, where it falls short, and which parts of the current hype won't survive contact with a real deal. No product pitch. Just a clear view from someone who has shipped it.
What we'll cover
- What MCP actually is.
- MCP vs API: what actually changed.
- Where is the S of Security in MCP?
- The advantages, honestly.
- The limits, equally honestly.
- How, Why, Where did Emma uses API connectivity vs MCP.
Who this is for
M&A lawyers, legal innovation and knowledge leads, and anyone being asked to sign off on connecting an AI tool to systems holding confidential client data. No engineering background needed. Pieter explains this the way he would explain it to a partner, not to a developer.
About the speaker
Pieter Buteneers is Co-Founder and CTO of Emma Legal, with a PhD in AI and 18+ years of applied machine learning experience. He founded Chatlayer.ai before building Emma. He is a regular speaker at MLcon, one of the leading European AI conferences, and runs workshops for DPOs on setting up an AI security framework. He speaks plainly, thinks in systems, and has no patience for AI hype that doesn't translate into better legal work.