> idk why we need MCP servers when LLMs can just connect to the existing API endpoint
Because the LLM can't "just connect" to an existing API endpoint. It can produce input parameters for an API call, but you still need to implement the calling code. Implementing calling code for every API you want to offer the LLM is at minimum very annoying and often error-prone.
MCP provides a consistent calling implementation that only needs to be written once.
yupp that's what UTCP does as well, standardizing the tool-calling
(without needing an MCP server that adds extra security vulnerabilities)
There's still an agent between the user and the LLM. The model isn't making the tool calls and has no mechanism of its own to accomplish this.
heh, relevant to the "do what now?" thread, I didn't recognize that initialism https://github.com/universal-tool-calling-protocol
I'll spare the audience the implied XKCD link