Found about MCP servers earlier this year, but only the last few weeks im getting my hands dirty with them. Im doing things with Typescript and Im struggling with integrating custom clients with mcp servers. Is anyone going through the same path?
PS: Im not asking about building an MCP server or connecting it to Claude Desktop, Cursor or something like that. That is easy, and Youtube is packed with videos about it. Im talking about custom frontends/clients and how to easily integrate them with MCP servers.
Title says it all, but in general i find that llm's are pretty bad with v3 components. both prop names and the general composition of components seem to have sufficient variance from v2 that the llm's often use the "wrong" paradigm. i like chakra, how can i use my tools more effectively so that it works well with gen ai? do you have context you set, or do you constantly mentioned you are using v3? appreciate any tips :)
