It turns out we've all been using MCP wrong. Most agents today use MCP by exposing the "tools" directly to the LLM. We tried something different: Convert the MCP tools into a TypeScript API, and then ask an LLM to write code that calls that API. The results are striking.

In my previous article , we explored Model Context Protocol (MCP) — a standardized way for LLMs to invoke tools or APIs with structured…

OpenAI-compatible API server for simonw's llm cli. Contribute to irthomasthomas/llm-model-gateway development by creating an account on GitHub.

Learn how to use the handwritting recognition Classification API (v1, 2023-10-08 12:56pm), created by LinhBau

I decided to have a poke around and see if I could figure out how the HTTP streaming APIs from the various hosted LLM providers actually worked. Here are my notes so far.

Read URLs or search the web, get better grounding for LLMs.

Say hello to Tavily, your AI researcher for rapid insights and comprehensive research.

A CLI Swiss Army Knife for ChatGPT. Contribute to npiv/chatblade development by creating an account on GitHub.