I view this as an another step in the push/pull between local things, remote things, local things remotely, thin clients, network partitioning, cloud, zero trust, etc...
The last cycle I remember of this IMO is iPython -> Jupyterhub/Jupyterlab. Of course, iPython has existed for a long time, though that change was made because data was too big to analyze locally and it turns out it was more convenient to centrally manage kernels/images/libraries for convenience.
MCP servers and Cursor/Windsurf changed that a bit, but it will end up centralized again at some point (or at least aggregated, if it's not already?). People are passing around lists of interesting MCP servers now, and that will be out of fashion in less than 12 months.
The last cycle I remember of this IMO is iPython -> Jupyterhub/Jupyterlab. Of course, iPython has existed for a long time, though that change was made because data was too big to analyze locally and it turns out it was more convenient to centrally manage kernels/images/libraries for convenience.
MCP servers and Cursor/Windsurf changed that a bit, but it will end up centralized again at some point (or at least aggregated, if it's not already?). People are passing around lists of interesting MCP servers now, and that will be out of fashion in less than 12 months.