MCP servers are all the rage right now, but half the experience lives on the client side - and most MCP clients still leave a lot on the table.

In this session, we’ll break down what makes a great MCP client:
What responsibilities does it own?
Where should common concerns like: discovery, auth, and session handling actually live?

When is it better to delegate to other tools in the ecosystem?
We’ll also take a hard look at the lesser-used parts of the MCP spec like roots, or, for example, dynamic tool config reloading, and show how small features like these can dramatically improve the use experience.