Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

MCP is a clumsy, frustrating, fiddly protocol that you shouldn't bother using. But anyway, I made an MCP server for

14,907 Aufrufe • vor 7 Monaten •via X (Twitter)

21 Kommentare

Profilbild von Daniel Howells
Daniel Howellsvor 7 Monaten

claude mcp add wiretext -- npx -y @wiretext/mcp

Profilbild von Christopher Man
Christopher Manvor 7 Monaten

I've been using this for the past hour, and I can say wiretext is actually shockingly good. I was trying to rebuild this from first principles, but your tool works so much better than mine. Good work.

Profilbild von Daniel Howells
Daniel Howellsvor 7 Monaten

So kind, thanks! It’s been fun, with some ridiculous problems to solve

Profilbild von Christopher Man
Christopher Manvor 7 Monaten

In my own project had a bunch of issues with arrows not rendering properly when ported to markdown, especially if the arrows cross through multiple boxes. I have no idea what type of magic you guys have done in order to solve this, but it's the main reason why I'm using your tool because it just works !

Profilbild von Wein Stanley
Wein Stanleyvor 7 Monaten

add arrow movement support please like canva Thanks sir🙏

Profilbild von Daniel Howells
Daniel Howellsvor 7 Monaten

huh, I don't use canva but I'm intrigued - what do you mean?

Profilbild von Wein Stanley
Wein Stanleyvor 7 Monaten

i cant move with my arrow keys in keyboard

Profilbild von Daniel Howells
Daniel Howellsvor 7 Monaten

gotcha. Will roll it into a release for Monday

Profilbild von Daniel Howells
Daniel Howellsvor 7 Monaten

actually I just pushed this update live ✌️

Profilbild von Wein Stanley
Wein Stanleyvor 7 Monaten

That was quick 👀 just tested and it works perfectly now. Thanks!

Profilbild von order and chaos at work
order and chaos at workvor 7 Monaten

all the cool kids are doing it tho

Profilbild von Daniel Howells
Daniel Howellsvor 7 Monaten

@mrdevelopersir I'm not cool and I did it anyway

Profilbild von order and chaos at work
order and chaos at workvor 7 Monaten

MCP makes you cool

Profilbild von maddada • ghostex.dev
maddada • ghostex.devvor 7 Monaten

Omg you know what this is sick for? Tell in the model to create the wireframe for me there, then I can adjust the ui a bunch and go back and forth, then just let the agent go with this wireframe as the starting point. I think this would result in MUCH better alignment with req.

Profilbild von Marchen
Marchenvor 7 Monaten

the honest frustration followed by shipping anyway is the most relatable dev thing

Profilbild von Vibhek Soni
Vibhek Sonivor 7 Monaten

Accurate take. MCP can feel rough but a thin server around a useful workflow still wins. Most teams dont need protocol purity, they need practical tools that ship

Profilbild von Nikolaj Sokolowski
Nikolaj Sokolowskivor 7 Monaten

Bookmarking this just in case mcp get cool again.

Profilbild von Daniel Howells
Daniel Howellsvor 7 Monaten

Nah it won’t

Profilbild von Ahmed IBRAHIM
Ahmed IBRAHIMvor 7 Monaten

What is the GitHub link, please ?

Profilbild von Prismor
Prismorvor 7 Monaten

said every MCP developer ever

Profilbild von Ashley Adamson
Ashley Adamsonvor 7 Monaten

@grok find me examples of other apps like this

Ähnliche Videos

New course: MCP: Build Rich-Context AI Apps with Anthropic. Learn to build AI apps that access tools, data, and prompts using the Model Context Protocol in this short course, created in partnership with Anthropic Anthropic and taught by Elie Schoppik Elie Schoppik, its Head of Technical Education. Connecting AI applications to external systems that bring rich context to LLM-based applications has often meant writing custom integrations for each use case. MCP is an open protocol that standardizes how LLMs access tools, data, and prompts from external sources, and simplifies how you provide context to your LLM-based applications. For example, you can provide context via third-party tools that let your LLM make API calls to search the web, access data from local docs, retrieve code from a GitHub repo, and so on. MCP, developed by Anthropic, is based on a client-server architecture that defines the communication details between an MCP client, hosted inside the AI application, and an MCP server that exposes tools, resources, and prompt templates. The server can be a subprocess launched by the client that runs locally or an independent process running remotely. In this hands-on course, you'll learn the core architecture behind MCP. You’ll create an MCP-compatible chatbot, build and deploy an MCP server, and connect the chatbot to your MCP server and other open-source servers. Here’s what you’ll do: - Understand why MCP makes AI development less fragmented and standardizes connections between AI applications and external data sources - Learn the core components of the client-server architecture of MCP and the underlying communication mechanism - Build a chatbot with custom tools for searching academic papers, and transform it into an MCP-compatible application - Build a local MCP server that exposes tools, resources, and prompt templates using FastMCP, and test it using MCP Inspector - Create an MCP client inside your chatbot to dynamically connect to your server - Connect your chatbot to reference servers built by Anthropic’s MCP team, such as filesystem, which implements filesystem operations, and fetch, which extracts contents from the web as markdown - Configure Claude Desktop to connect to your server and others, and explore how it abstracts away the low-level logic of MCP clients - Deploy your MCP server remotely and test it with the Inspector or other MCP-compatible applications - Learn about the roadmap for future MCP development, such as multi-agent architecture, MCP registry API, server discovery, authorization, and authentication MCP is an exciting and important technology that lets you build rich-context AI applications that connect to a growing ecosystem of MCP servers, with minimal integration work. Please sign up here!

Andrew Ng

142,256 Aufrufe • vor 1 Jahr