We re thrilled to announce MCP Discovery, the newest upgrade to Toolhouse that makes connecting your agents to any Model Context Protocol (MCP) server as easy as writing your idea.
Why does it feel like every developer in the bay area announces ANOTHER MCP library to write client/servers for AI...the USB-C of AI they say, it feels to me like the nightmare of AI, because everything moves so fast and everyone is building more stuff (and barely maintaining it)
There are a lot of AI frameworks to begin with: LangChain. LlamaIndex. AutoGen. CrewAI. DSPy. OpenDevin. Semantic Kernel... They re all trying to answer one basic question:
'The best way to reliably interact with an LLM so that you can bolt things like memory, tools, and MCP to your AI agent'
I've noticed recently that YouTube are offering me very tempting free trials to upgrade to their ad-free version which also includes original premium content. While I was excited by the idea of ad-free YouTube when they announced the news a few years back, as a frugal person I never made the investment. Do you pay for ad-free YouTube, and if so, do you feel it's worth it?
ToolhouseConnect AI to the Real World
