The Higsfield MCP server revolutionizes AI content creation by providing a unified platform to access and automate the use of diverse, rapidly evolving AI tools through Claude Code, enabling efficient, large-scale content generation.
Mind Map
Klik untuk perbesar
Klik untuk menjelajahi mind map interaktif lengkap
Claude Code has a content creation
problem and Higsfield's brand new MCP
server just solved it. Instead of having
to individually connect every AI content
creation tool to Claude Code, which you
kind of have to do since the best ones
change from week to week, we can now get
them all in one place via the MCP
server. And this just isn't a
convenience win. This means we can now
reliably automate large portions of our
content creation process with the best
AI tool for the job. So today I'm going
to show you exactly how to install this
tool and the process I use to create
this piece of content that got 100,000
views in less than 24 hours using the
Higsfield MCP server. So why does the
Higsfield MCP server even matter? Why
should you care? Well, I alluded to it
in the intro, and there's two reasons.
First one is the fact that we now have a
single pathway to getting access to
every single AI content creation tool.
Because up until now, we really haven't
been able to do that programmatically.
Instead, you had to individually connect
all these tools to claude. Giant pain in
the butt. Nobody did this because
everyone had its own API, its own
payments, even if the API was publicly
available, which in some cases it
wasn't. And so, you were kind of locked
into the one or two you actually used.
Problem with that is the best ones
change all the time. Last week, Dano
Banana Pro was on top. Guess what? Now
it's GPT images too. 6 months ago VO3
was the top dog. A month ago it was
Cling and today it's Seed Dance. Are you
using the best tool for the job? Chances
are you weren't if you were set up like
this. But now alls I have to do is be
connected to the Higsfield MCP. And
boom, I can now connect to all of these
and more. And by more, I mean there's 17
image models, 14 video models, and we
have access to a lot of the Higsfield
proprietary models. But the real unlock
isn't the convenience. It's the fact
that since it's an MCP server, we can
now automate a lot of these processes
via Cloud Code. For example, I can
create an automation where every single
day Claude Code takes a look at GitHub
and it says, "Hey, what are the top
trending AI repos for this week, for
this month, brand new ones that just got
released?" It's going to take that
information. It's going to bring it back
inside of Cloud Code, and it's now going
to structure it in a way that I could
use for some sort of social media posts.
In our example, it will be a carousel.
Alongside that, it will then create a
prompt for the images so that we can get
images like these, but it has to copy
and the information from the GitHub that
it just pulled. It's then going to send
all that information to Higsfield, which
will then call on GPT images 2 to create
all that for us. It then brings it back
into Cloud Code. And voila, we just have
a completely automated content creation
process. From there, I can manually
review them. I can have Claude Code post
them. But the point is I can now
automate some sort of flow. You could
automate even more of it where I'm
grabbing information from some outside
place in this case GitHub. I'm then
analyzing the information inside of
Cloud Code. I'm taking that analyzed
information and I'm turning it into some
sort of content prompt which gets sent
to the Higsfield MCP. And then it brings
it all back to me and I have a nice
deliverable and I really haven't even
lifted a finger. So that's the real
power that is unlocked via this MCP
server. So you combine these two things
and we are really turning Claude Code
into a marketing machine. So let's talk
about the install. First of all, you are
going to need a Higsfield account. I
will have a link to that in the
description. If it wasn't clear by now,
Higsfield is a one-stop shop for all
things AI content creation related.
Next, we need to install the MCP. And
there's really two ways to do this. One,
we can go inside cloud.ai and just set
up a connector. Two, we can just do it
inside the terminal via Cloud Code.
Setting up the connector is very easy.
You'll just go to claw.ai. You'll head
to settings. You will go to connector.
You will go to add custom connector.
You'll copy this, paste that in there,
and hit add. You'll then hit connect.
And it will ask you to log in. And boom,
there we go. I can now essentially call
any of these audio, video tools, image
tools that live inside of Higsfield from
Claude itself, the web app. And I can
also do it from the desktop app. So
inside the chat I said use the Higsfield
connector and create an image talking
about the power of cloud code plus
Higsfield using GPT image 2. And you can
see it's calling the model right now. It
will ask you for some permissions. You
can see the actual prompt it's sending
in JSON. And we see the image in
progress. The nice thing about doing
this inside of the actual chatbot
application or on your desktop Cloud app
is the fact that the images will be
generated in line, which means I'm
actually going to be able to see them.
And remember, there's a lot more we can
do than just simply create an image or a
video. There's actually a lot going on
under the hood with this MCP. You can
ask Claude itself to explain it to you,
but I also have this guide that I wrote
up that I will put inside of the free
school community. There will be a link
to that in the description. And here's
the image it created for us. And as I
scroll over it, you can see I have a few
options. I can recreate it. So
essentially just send the prompt there
again. I can animate it. So send it to a
video editor. I can edit it. And so what
it does is it brings up essentially
another prompt. In this case, it would
send it to Nano Banana 2, but I could
change that to, you know, like GPT
image 2. It links the reference image so
it knows what it's editing. And then you
just put your prompt in there. So pretty
intuitive in terms of how you mess with
this inside of the chat application. But
let's talk about what I think is the
biggest unlock and that's using it
inside of Claude Code. So to set up the
MCP server inside of Claude Code, super
simple as well. Literally just going to
use plain language and say set up this
MCP server for me. You'll just head back
to this page which is the Higsfield MCP
page. I'll link that as well. You'll do
custom connector.
You'll paste it in there and it's going
to go to work. It's going to set it up
for you and it will also give you a link
to go through the same authentication
process you just saw me do on the web
app. Now to confirm it's set up just do
for/mcp and you should see Higsfield
connected. If you don't just have a back
and forth with cloud code and it will
walk you through the steps to make sure
it's connected. You may just need to
exit cloud code and spin it back up. Now
at this point once the MCP server is
connected we can now use basically any
AI content creation model from the
terminal through natural language. So if
I tell cloud code create me 16 different
images with GPT images too it will do
that for you and it will just download
them and you can even tell it hey I want
you to bring up the images for me. The
only downside with the terminal is
obviously we can't see the images inside
the terminal itself. But hey, what we
really want to do is we want to figure
out how to put this inside of an
automation, how to script it. But
natural language prompting is simple and
exact same process as I showed you on
the web app. So let's go through this
process. So what we first need is we
need to be able to grab information from
GitHub and bring it back into cloud
code. And you can see that right here.
This is an automation that runs every
single morning and it grabs the top 10
trending GitHub repos this week that
were created in the last 7 days and
ranks them based on stars. It gives me a
quick description all this sort of
stuff. And I can also see the top five
trending over the last month. And again,
these are just new ones that are just on
the scene. Now, to create this for
yourself is actually really simple. I
have the whole breakdown inside of Chase
AI plus, but you can literally just
prompt Cloud Code and say, "Hey, can you
create me an automation that checks
GitHub for this every single day?"
There's no API you need to set up or
anything like that. But what I want to
do is I want Claude Code to take a look
at this information and I want it to
essentially turn it into a carousel. And
if you're not familiar with carousels,
they're just posts like this. We'll have
some sort of cover page. This one is top
five Claude Code front-end skills, but
instead we'll do top five Claude Code
GitHub repos or top five AI repos. We'll
see what Claude Code comes up with. I'm
going to give it the reference images
that you see here. So, I'll give it the
cover page and I will give it some of
these, you know, body slides, so to
speak, because I'm going to want it to
be in the same sort of style. And we'll
see what it comes up with. So, I'll feed
it this. I'll feed it the GitHub
information. And then cloud code should
say, okay, based on everything in this
GitHub, based on the reference images,
here's what we should think about in
terms of coming up with a prompt. So I
gave Cloud Code a pretty simple prompt.
I said, take a look at our GitHub
trending data for today. What I just
showed you inside of Obsidian, I want to
create a carousel talking about that
information. We could call it top five
trending AI repos this month or
something like that. I want it turned
into slides like this, cover plus body
slides. And then I fed them those four
slides or those three slides. And then I
just said, "Let's talk about it before
sending it off for content creation."
Now, what we're doing here is we're sort
of manually going through each step. So,
we already did the content. Now, we're
going to talk about it before we send it
off here to Higsfield. What you would
actually want to do after you kind of
got this to a place you liked and you've
continued doing this over and over is
instead of me being, "All right, now
let's do GitHub. Now, let's talk about
it. Now, let's push the prompts. We
could actually turn this entire thing
into like one large call it you could
call it like Higsfield skill or really
any skill you want to give it whatever
name you want. But you can automate this
entire process and you could have
something that every single day, you
know, right after it hits GitHub in the
morning and says, "Hey, here's the top
10 repos." Well, why don't we just turn
that into a post? You could have a
carousel every single day that says,
"Hey, here are the top 10 trending AI
repos for today." You know, that's
actually like somewhat relevant content
that people would actually like. And
this is an easy way to create it.
Don't steal my idea. So, Claude is
telling us, "Hey, I pulled today's
trending files. It's just repeating the
top five GitHub repos for this month. It
has some thoughts. Claw code is
suspicious." Yeah. Yeah. Little sketch.
talks about the hook angle, talks about
the title
as well as the layout and the hero image
and all these things. So, here's the
prompt I gave it. It talked about using
a carousel skill, which is actually an
irrelevant skill for this. It has
nothing to do with Higsfield MCP. So, I
said, "I ignore that skill. Let's start
with the cover slide." So, that main
slide that everyone's going to see, I
want it done in the same style as a
reference image I gave you. Use your
copy. Use Higsfield's MCP. You use GPT
images, too, for variations.
And that's kind of wordy, which is
totally why you would eventually want to
turn this into an actual skill if this
is something you're doing a lot. So
remember, we are trying to create
something that looks like this because
we are feeding this exact reference
image in there and we're saying do
something similar. Just change up the
copy, change up the title. So it just
came back with the four variants. It
took about 5 minutes. Understand the
speed at which this is going to happen
is going to be totally dependent on the
model you use and the quality. So for
GPT image 2, I was doing high quality 2K
and I wanted four variations. Another
thing you need to think about when you
do this is the way the MCP works is you
were just sending a request. It's not
going to hit you back up when it's done.
So you need to tell Claude Code, hey, I
want you to pull Higsfield every 60
seconds, 90 seconds to see if it's done
and then bring it back to me. So here's
the four variations. We got one, two,
three, four. Now, we pretty much told it
do the exact same thing. Just put our
new copy on it. And it did exactly that.
Actually, I think it looks pretty good.
If I wanted to edit something, I'd
probably get rid of the list down here.
I'm not sure if I am am in love with the
Chase AI up top, but point being, if you
tell it, hey, use this reference image,
it's sending the reference images just
like if you were in there doing this
manually. And so, step one, giving it
some sort of reference image to use as a
cover, did a solid job. Now, let's see
how well it does here in terms of these
body slides. Now, you'll notice here
we're actually grabbing some stuff from
the GitHub page itself. So, what I'm
going to tell Cloud Code to do here is
find your own assets that we could use
as reference images that would make
sense for the value page. Again, like we
have the full power of Cloud Code here
to help improve the quality of the work.
So, I said first slide looks good. Let's
move into the body slide. Use the first
GitHub repo that's up. And then I said,
hey, go ahead and figure out what assets
we need from the GitHub itself to be
used in this generation. Research that
GitHub, pull assets as needed, add them
to the MCP request as well. So, I'm
having it do quite a bit here, like go
on the internet, find the appropriate
repo, grab what you need from there,
bring it in to your prompt, and then
push it to the MCP. And here's what it
came back with, and it was giving us the
slide for awesome.md
for reference. This is what the
awesomedesign.md GitHub looks like. So,
pretty close. I think that looks good.
And it gave us four variations, all that
are slightly different. Nothing really
popping out, but I think it did a really
good job. It also definitely matches the
aesthetic that we gave it here in the
reference image. So, really, really
good. And now all we would do is repeat
that exact same process for the rest of
the slides. And we wouldn't have to go
one by one at this point. We could
essentially have it rapid fire all of
them. And so you could see how easily we
can turn something like this into a
content machine, especially if we have
some resource like daily updated GitHub
repo list. This is just like an
evergreen content thing that people
would be interested in and I can do it
all from here. I can turn this into one
single skill with the MCP server really
powering the creative side. Now, the one
thing I will also mention is you don't
have to go full AI image generation for
all these things. Like you could also do
sort of a hybrid style where we use
Higsfield for the cover image because
this is where the aesthetics is really
going to play a big role. And then maybe
instead you want to go lower cost, lower
tokens and for the sort of body slides
you use like HTML or something. You have
cloud code essentially generate that via
code. Lots of ways to approach this, but
the big thing is is we have we have
options now. We have options now with
this MCP server. So, that's where I'm
going to leave you guys for today. All
the links for this stuff can be found
inside the the description. Make sure to
check out Chase AI Plus if you want to
get your hands on my Cloud Code
Klik teks atau cap waktu mana pun untuk melompat ke momen tersebut dalam video
Bagikan:
Sebagian besar transkrip siap dalam waktu kurang dari 5 detik
Salin Satu Klik125+ BahasaCari KontenLoncat ke Cap Waktu
Tempel URL YouTube
Masukkan link video YouTube apa saja untuk mendapatkan transkrip lengkap
Formulir Ekstraksi Transkrip
Sebagian besar transkrip siap dalam waktu kurang dari 5 detik
Pasang Ekstensi Chrome Kami
Dapatkan transkrip seketika tanpa meninggalkan YouTube. Pasang ekstensi Chrome kami untuk akses satu klik ke transkrip video apa pun langsung di halaman tontonan.
