This Claude MCP GitHub AI AGENT Changes EVERYTHING!

[@TheBuzzati]

Oh I get this MCP thing now lol. Thanks for explaining it so well.

[@xkiran]

Great video. My understanding of MCP just got better. It was not that easy to read up all the Anthropic documents and figure out. Thank You!!

[@Ms.Robot.]

Your plans are top notch❤.

[@moemoe86420]

when i did the git issue problem it failed every time saying its unable to access the repo despite it already created the repo and has all access

[@AndyBrooks]

How much do the API calls total up costing by the end of these projects?

[@jootjemootje]

That's the good part, because it's part of the Claude subscription already so you don't pay anything else for api calls to Claude 🙂

[@calmsimon]

If you running Claude hard you could probably do 10-20/day. That’s doing a crazy amount of shit though. Really it’s like 1-5

[@nguyenangkhanh1485]

So, essentially, it will automatically integrate tools for us with the existing ones managed by Anthropic, correct? From what I understand, the MCP primarily runs workflows using pre-configurations provided by Anthropic. If that’s the case, is there any way for us to modify these configurations?

[@ashutoshshukla2325]

Hum Hindi mein ise sun pare yahi bahut behatareen hai!

[@DmitryAvramenko]

Please share your version of the server with your new tools. Would like to play with it. Great video

[@clamr6122]

Could you try forking one of the server repos? Then have Claude read the file and add additional tools to allow it to do jobs it doesn't yet have the tools for?

[@henriquematias1986]

The question i have is how to leverage MCP / Claude API without having to run the desktop app? For instance, what if we want to use the same tools but on a command line interface. instead? Perhaps we could use them several instances at the same time? How is that different from "tool use" on AI SDK by vercel for instance? It seems to have a lot of overlap..

[@JoshuaKolden]

MCP is an attempt to creat an open standard for tool use that provides well defined interfaces for client, server and LLM function calling. It is designed so that you can use custom solutions for any of those three elements. You can use an existing server in your own client such as your command line tool. You could replace the Claude backend with ChatGPT or a local model, etc. What most people are demonstrating right now is just how easy it is to create and modify servers. That alone is pretty impressive, but considering it’s only a third of what MCP offers MCP is a very exciting new bit of kit.

[@henriquematias1986]

@@JoshuaKolden absolutely! i wonder if we could still use claude as backend and MCP tools but instead use a command line tool so we don't have to use the mouse and keep clicking "allow" for instance. any ideas on how to do that? i saw documentation on how client and server works but not how to have an AI such as claude provide the clients and let it use the clients from a script as opposed to the desktop GUI.

[@DavidDji_1989]

Would be great to make an agent that can play Pokemon TCG

[@mognog]

Great video & fab channel. However, the LLMs are only really good for small amounts of code. Once your project becomes complex or large, you get duff code generated all the time. So i think you will spend more time in cursor than in Claude desktop. If you have cursor setup with a github account, create a brand new project and then just push to github via the menu. It will just ask you for public or private. Then in composer ask it to create your application. Finally in composer ask it to create your readme file. Push the results. Although using MCP is interesting i dont see you gaining anything. A different example with something that saves time or is not doable in cursor would be good.

[@bencium-agentic-ai]

claude desktop app runs into MCP fatal error (github api) and limit restrictions.

[@mesparzajr]

Did you find a solution

[@bencium-agentic-ai]

@@mesparzajr not yet

[@tronfm]

Is MCP the "Master Control Program" from the TRON movie? :-)

[@maxziebell4013]

Wispr Flow… is just the best

[@jacekwojcieszynski8368]

do you run it on MacOS?

[@lithium534]

I would love to test out your version. If you would add it somewhere please let me know.

[@SebKrogh]

I cannot wait for an N8N MCP

[@freddiechipres]

What would that look like?

[@pushingpandas6479]

wont happened

[@SebKrogh]

@@freddiechipreswell if it can read and write to the software - it would be able to view, review, debug, edit and write automation flows for you. N8N flows are basically Json under the hood - så it wouldn't be that hard. If you export a flow and upload it to Claude it understands it pretty deeply already. This would just be that OK steroids.

[@SebKrogh]

@@pushingpandas6479i am pretty certain it will? Why wouldn't it?

[@stevensexton5801]

I've not had any luck creating a MCP other than the SQL example running on Windows

[@permiek]

Master Control Program

[@patruff]

We NEED custom MCPs. I'll make one soon, but basically...you can't delete files (or git rm)

[@EduardsRuzga]

I made so called Server Commander before for ChatGPT CustomGPTs It gave terminal access to ChatGPT as action to call. That allows to run commands including deleting files or running things like tests.

[@LudwikCSiadlak]

How do I get MCP on my Claude account ?

[@NITHZAEL92]

Watch the video above this one

[@danialothman]

I wonder how much users on free plan can do with this

[@drummermike5150]

I'm on the free plan and the only one I've been able to get to work is the SQLite server. I've tried PostgreSQL and GitHub with no luck. I'm getting this in the log file so not sure what is going on - Connected to MCP server postgres! and Connected to MCP server github!

[@HemangJoshi]

Why dafuq the entheopic desktop app for linux does not exist while 80% of the software developer community and almost all 100% of the servers run on Linux

[@GeeDeeDee]

Where did you pull that statistic from?

[@francycharuto]

A lot of flaws so far...

[@firemontana1284]

Aru u making money of ai?

[@AaronSof]

@@firemontana1284 are you? I want to. I'm trying.

[@mik3lang3lo]

❤

[@clamr6122]

There's a lot of money to be made from an app that does this reliably...

[@gehdochnicht]

lol if everyone can do it even for free why would anyone pay for it?

[@youtubeccia9276]

i got this video translated in german? terrible, why?

[@fabiankliebhan]

Bei mir wurde nur der Titel auf deutsch angezeigt was ich auch schon seltsam finde… Man kann es aber sicher irgendwie deaktivieren. KZbin scheint da grade sehr viel rum zu experementieren

[@youtubeccia9276]

@ zweiteres dachte ich mir auch schon, hab aber nichts gefunden …

[@youtubeccia9276]

@ danke für dein Input, sind wir jetzt Freunde? 😃

[@fabiankliebhan]

@@youtubeccia9276 aber natürlich 😁

[@youtubeccia9276]

@@fabiankliebhan feine sache :)

[@silentphil77]

Why is windows such a hassle

[@gehdochnicht]

What's so complicated? It's 99.5% the same.

[@silentphil77]

@@gehdochnicht obviously it's not

[@gehdochnicht]

@@silentphil77 if you follow 100% of a guide for mac then clearly it won't work even if it's just 0.5% that is different. Why don't you follow a guide for Windows or say which problem do you have?

[@silentphil77]

@@gehdochnicht because back then there wasnt any for windows mate

[@hadexxx]

What about running the project to make sure it really runs. I’ve had complex projects where claude, chatgpt, etc think it’s good but it won’t run

[@squirrel3244]

hey did you used to live with Dan in Granby Co? if not you have doppelganger. if it is you. its Squirrel. good to see ya i got the tv off ya. id see ya walking past the train museum.