Ultimate No Code MCP Setup Guide (Self-Host, Installation, Common Issues)

Today we're going to be going through the full setup of connecting MCP servers to EnnetN. I'm going to walk through how you self-host your EnnetN, I'm going to walk through how you can install the community node, and then how to actually set up the community node. The best part is you don't have to open up a terminal or a shell and type in any install commands. All we have to do is connect to the servers through EnnetN. So if that sounds like something that interests you, let's dive into it. Make sure you guys stick around for the end of this one because we're going to talk about the current limitations of these MCP nodes, We're going to talk about some problems you may face that no one else is talking about, and really what does it mean to actually be able to scale these agents with MCP servers. Now there are a ton of different platforms that you can use to host NNN. The reason I'm using Elestio is because it's going to be really simple for deploying and managing open-source software, especially with something like NNN. You can pretty much deploy it in just a few clicks and it's going to take care of installation, configuration, security, backups, updates, all this kind of stuff. So there's no need for you to have that DevOps knowledge because I certainly don't, so that's why we're going with Alestio. It's also SOC 2 and GDPR compliant, so that's important. Anyways, like I said, we're gonna be going through the full process, so I'm gonna click on free trial. I'm gonna sign up with a new account, so I'm gonna log out and sign up as a new user. Okay, now that I entered that, we're already good to go. The first thing I'm gonna do is set up a payment method so that we can actually spin up a service. So I went down to my account in the left-hand side, and then I clicked on payment options, and I'm gonna add a card real quick. Now that that's been added, it's gonna take a few minutes for our account to actually be approved, so I'm just gonna wait for that. You can see we have a support ticket that got opened up, which is just waiting for account activation. Also, here's the approval email I got. Just keep in mind it says it'll be activated in a few minutes during business hours, but if you're doing this at night or on the weekends, it may take a little longer. Okay, there we go, we are now activated. So I'm gonna come up here to Services, and I am going to add a new service. What we're gonna do is just type in N8N, and it's gonna be a really quick one-click install. Basically, I'm gonna just be deploying on Hetzner as a cloud provider. I'm gonna switch to my region, and then you have different options for service plans. So these options obviously have different numbers of CPUs, different amount of RAM and storage. I'm gonna start right now on just the medium. I would keep in mind that MCP servers can be kind of resource intensive. So if you are running multiple of them and your environment is crashing, then you're probably just gonna want to come in here and upgrade your service plan. So we can see down here, here's the estimated hourly price, here's the plan we're going with, and I'm gonna go ahead and move forward. Now we're going to set up the name. So this will pop up as your domain for your n8n environment. Then I went ahead and called this n8n-demo. What you can do here is you can add more volume. So if you wanted to, you could increase the amount of storage, and as you can see down here, it's going to increase your hourly price. I'm not going to do that, but you do have that option. And then of course you have some advanced configuration for software updates and system updates. Once again, I'm just going to leave that as is. And then you can also choose the level of support that you need. You can scan through your different options here. Obviously you'll have a different price associated with it, but on the default plan, I'm just gonna continue with level 1 support. And now I'm gonna click on create service. Okay, so I don't have enough credits to actually deploy this service, so I'm gonna have to go add some credits in my account. So back in the account, I went to add credits, and now that I have a card, I can actually add some credits. So I'm gonna agree to the terms and add funds. Payment successful, nice, we have some money to play with down here. We can see 10 credits. This is also where we'll see how much we're spending per hour once we have this service up and running. Unfortunately, we have to do that all again, so let me get back to the screen we were just on. Okay, now we're back here. I'm gonna click Create Service. We're deploying your service, please wait. And this is basically just gonna take a few minutes to spin up. Okay, so now what we see is the service is currently running. We can click into the service and we should be able to get a link that's gonna take us to our NNN instance. So here's what it looks like. We can see it's running. We have all these different tabs and all these different things to look through. We're gonna keep it simple today and not really dive into it. But what we're gonna do is come down here to our network and this is our actual domain to go to. So if I select all of this and I just click Go to this app, it's gonna spin up our NNN environment. And because this is the first time we're visiting it, We just have to do the setup. Okay, so once we have that configured, gonna hit next. We have to do some fun little onboarding where it's gonna ask us some questions right here. So then when you're done with that, you just gotta click get started and you now have this option to get some paid features for free. I'm gonna hit skip and we're good to go. We are in n8n. So what's next is we need to install a community node. So if you come down here to your settings and you click on settings, um, you can see you're on the community plan. We can go all the way down here to community nodes and now we have to install a community node. So in the description, we have the GitHub repository for this n8n nodes MCP that was made by Nerding, and you can see there's some information on how to actually install this. But all we have to do is basically just copy this line right here. I'm just going to copy n8n-nodes-mcp, click on install community node, put that in there, hit understand. And so the reason you can only do this on self-hosted is because these nodes are not a native verified node from n8n. So it's just like, you know, we're downloading it from a public source, at least the code, and then we hit install. Package installed. We can now see we have one community node, which is the MCP. Cool. So I'm going to leave my settings and I'm going to open up a new workflow. And we're just going to hit tab to see if we have the actual node. So if I type in MCP, we can see that we have MCP client and we have this little block, which just means that it is part of the community node. So I'm going to click into here and we can see we have some different options. We can execute a tool. We can get a prompt template. We can list available prompts, list available resources, list available tools. And read a resource. Right now, let's go with list available tools. The main one we'll be looking at is listing tools and then executing tools. So quick plug for the school community. If you're looking for a more hands-on learning experience, as well as wanting to connect with over 700 members who are also dedicated to this rapidly evolving space, then definitely give this community a look. We have great discussions, great guest speakers, as you can see. We also have a classroom section with stuff like building agents, vector databases, APIs, and HTTP requests. Step-by-step builds, all the live calls are recorded, all this kind of stuff. So if this sounds interesting to you, then I'd love to see you in a live call. Anyways, let's get back to the video. So obviously we have the operation, but we haven't set up a credential yet. So now what you're gonna do is go to a different link in the description, which is the GitHub repository for different MCP servers, and we can pretty much connect to any of these, like I said, without having to run any code in our terminal and install some stuff, at least because we're hosting in the cloud. If we're hosting locally, it may be a little different. Okay, so I've seen a ton of tutorials go over like Brave Search or Firecrawl, so let's try to do something a little more fun. I think first we'll start off with Airbnb because this one is going to be free. You don't even have to go get an API key, so that's really cool. So I'm going to click into this Airbnb MCP server. There's a bunch of stuff going on here, and if you understand GitHub and repositories and some code, you can look through like the Dockerfile and everything, which is pretty cool. But for us non-techies, all we have to do is come down here. It's going to tell us what tools are available. but we just need to look at how to actually install this. And so all we're looking for is the MPX type installer. And so after my testing, I tried this one first, but it wouldn't let us execute the tool because we need to use this thing that is ignore robots.txt, which just basically lets us actually access the platform. So you can see here we have a command which is MPX, and then we have an array of arguments which is -y, this openbnb thing, and then also the ignore robots.txt. So first of all, I'm just going to grab the command which is MPX. Copy that, go back and end it in, and we're going to create a new credential. This one's going to be for Airbnb. So I'm just going to name this so we have it kept, and then we're just going to paste the command right into there, MPX. Now we can see we have arguments to fill out, so I'm going to go back into that documentation. We can see the arguments are -y, and then the next one is the OpenBnB, and then the next one is ignore robots.txt. So we're going to put them in one by one. So first is the -y. Now I'm going to go back and grab the @openbnb put a space and then paste it in there, and then I'm gonna put another space, and then we're gonna grab this last part, which is the ignore robots.txt. So once we paste that in there, we can basically just hit save. As you can see, we've connected successfully. The credential is now in our space, and we didn't have to type in anything in a terminal. And now if we hit test step, we should be able to pull in the tools that this MCP server gives us access to. So it's as easy as that. As you can see, there are two tools. The first one is Airbnb Search. Here's when you use it, and then here's the schema to send over to that, tool. And then the second one is Airbnb listing details. Here's when you want to use that, and then here's the schema that you would send over. And now from here, which is really cool, we can click on another node, which is going to be an MCP client once again. And this time we want to execute a tool. We already have our credential set up, we just did that together. And now all we have to do is configure the tool name and the tool parameters. So just as a quick demo that this actually works, the tool name, we're going to drag in Airbnb_search, as you can see. And then for the parameter, we can see these are the different things that we need to fill out. And so all I'm gonna do is just send over a location. So I obviously hardcoded in location equals Los Angeles. That's all we're gonna try. And now we're gonna hit test step, and we should see that we're getting Airbnbs back that are in Los Angeles. There we go. We have a ton of different items here. So let's actually take a look at this listing. So if I just copy this into the browser, we should see an Airbnb, Arts District Guesthouse. This is in Culver City, California. And obviously we could make our search more refined if we were able to also put in like a check-in and checkout date, how many adults, how many children, how many pets. We could specify the price, all this kind of stuff. Okay, cool. So that was an example of how we search through an MCP server to get the tools and then how we can actually execute upon that tool. But now if we want to give our agent access to an MCP server, what we would do is obviously we're going to add an AI agent. We are first of all going to come down here, give it a chat input so we can actually talk to the agent. So we'll add that right here. And now we obviously need to connect a chat model so that the agent has a brain. And then give it the MCP tools. So first of all, just to connect a chat model, I'm just going to grab an OpenAI. I'm sorry for being boring, but all we have to do is create a credential. So if you go to your OpenAI account and grab an API key, so here's my account. As you can see, I have a ton of different keys, but I'm just going to create a new one. This is going to be MCP test. And then all we have to do is copy that key, come back and end it in, and we're going to paste that right in here. So there's our key, hit save, we'll go green. We're good to go. We're connected to OpenAI. And now we We can choose our model, so 4M Mini is going to work just fine here. Now to add a tool, once again we're going to add the MCP client tool right here, and let's just do Airbnb one more time. So we're connected to Airbnb list tools, and I'm just going to say, what tools do I have? And what's going to happen is it errored because the N8N nodes MCP tool is not recognized yet, even though the MCP nodes are. So we have to go back into Alestio real quick and change one thing. So coming back into the GitHub repository for the n8n-mcp-node, we can see it gives us some installation information, right? But if we go all the way down to how to use it as a tool, if I can scroll all the way down here. So here is an example of using it as a tool. You have to set up the environment variable within your hosting environment. So whether it's Elestio or Render or DigitalOcean or wherever you're doing it, it'll be a little different, but you just have to navigate down to where you have environment variables. We have to set n8n_community_package_allow_tool_usage we have to set that to equal true. So I'm gonna come back into our Alestio service, and right here we have the software, which is N8N version latest. And what we can do is we can, you know, restart, view app logs, we can change the version here, or we can update the config, which if we open this up, it may look a little intimidating, but all we're looking for is right here. We have environment, and we can see we have like different stuff with our Postgres, with our webhook tunnel URLs, all this kind of stuff. And so at the bottom, I'm just gonna add a new line And I'm just gonna paste in that command we had, which was n8n.community_packages.allow. And then instead of an equal, I'm going to put a colon. And now we have that n8n.community_packages.allow is set to true. And I'm just adding a space after the colon. So now it's pink. And all we're just gonna do is hit update and restart. And so this is going to respin up our instance. Okay, so it looks like we are now finished up. I'm gonna cl— go ahead and close out of this. We can see that our instance is running. So now I'm gonna come back into here and I actually refresh this. So our agent's gone. So let me get 'em back real quick. Alright, so we have our agent back. We're going to go ahead and add that MCP tool once again right here. We are going to have our credential already set up. The operation is list tools. And now let's try one more time asking it, what tools do you have? And it knows to use this node because it's the operation here is list tools, so it's going to be pretty intelligent about it. Now it's able to actually call that tool because we set up that environment variable. So let's see what Airbnb responds with as far as what tools it actually can use. Cool, so I have access to the following tools: Airbnb search and listing details. Now let's add the actual tool that's going to execute on that tool. So Airbnb, once again, we have a credential already set up. The operation, we're gonna choose execute tool instead. And now we have to set up what is going on within this tool. So the idea here is that when the client responds with, okay, I have Airbnb search and I have Airbnb listing details, the agent will then figure out based on what we asked Which one do I use? And the agent has to pass that over to this next one, which is actually going to execute. So what we want to do here is the tool name cannot be fixed because we want to make this dynamic. So I'm going to change this to an expression and I'm going to use the handy fromAI function here, which is basically we're just going to tell the AI agent, okay, you know, based on what's going on, you choose which tool to use and you're going to put that in here. So I'm going to put in quotes tool. And then I'm going to just define what that means. And in quotes, after a comma, I'm going to say the tool selected. So we'll just leave it as simple as that. And then what's really cool is for the tool parameters, this is going to change based on the actual tool selected because there's different schemas or parameters that you can send over to the different tools. So we're going to start off by just hitting this button, which lets the model define this parameter. It's going to get back what— not only what tool am I using, but what schema do I need to send over. So it should be intelligent enough to figure it out for simple queries. So let's change this name to Airbnb execute. I'm gonna change this other one to Airbnb tools, and then we'll have the agent try to figure out what's going on. And just a reminder, there's no system prompt in here. It literally just says you're a helpful assistant. So we'll see how intelligent this stuff is. Okay, so I'm asking it to search for Airbnbs in Chicago for 4 adults. Let's try that off. We should obviously be using the Airbnb search tool. And then we want to see if it can fill out the parameters with a location, but also how many adults are gonna be there, because earlier all we did was location. So we got a successful response already back. Once this finishes up, we should see potentially a few links down here that actually link to places. So here we go, luxury designer penthouse, Gold Coast. It's apartment, it has 3 bedrooms, 8 beds, so that definitely fits 4 guests. And you can also see it's gonna give us the price per night as well as, you know, the rating and just some other information. So let's click into this one real quick and we'll take a look, make sure it actually is in Chicago and it has all the stuff. This one does have 10 guests, so awesome. And we can see we got 5 total listings. So without having to configure, you know, here's the API documentation and here's how we set up our HTTP request, we're already able to do some pretty cool Airbnb searches. So let's take a look in the Airbnb Execute tool. We can see that what it sent over was a location as well as a number of adults, which is absolutely perfect. The model was able to determine how to format that and send it over as JSON. And then we got back our actual search results. And now we're gonna do something where you actually do need an API key because most of these, you are going to need an API key. So we're gonna go ahead and do Brave Search because you can search the web using Brave Search API. So we're gonna click into this. And all we have to do is once again, we can see the tools here, but we wanna scroll down and see how you actually configure it. So the first step is to go to Brave Search and get an API key. You can click on this link right here and you'll be able to sign in and get 2,000 free queries, and then you'll grab your API key. So I'm gonna log in real quick. So it may send you a code to your email to verify it. You'll just put in the code, of course, and then we're here. As you can see, I've only done one request so far. I'm gonna click on API keys on this left-hand side, and we're just gonna copy this token and then we can put it into our configuration. So let's walk through how we're gonna do that. So I'm gonna come in here and add a new tool. We're gonna add another MCP client tool. And we're going to create a new credential because we're no longer connecting to Airbnb's server, we're connecting to Brave Search server. So create new credential. Let me just name this one real quick so we don't get confused. And then of course we have to set up our command, our arguments, and our environments. And this is where we're going to put our actual API key. Okay, so first things first, the command. Coming back into the Brave Search MCP server documentation, we can see that we can either do Docker, but what we're doing every time we're connecting to this in N8N is going to be MPX. So our command once again is npx. Copy that, paste it into the command, and now let's go back and get our arguments, which is always going to start off with -y. Then after that, put a space. We're gonna connect to this MCP server, which is the Brave Search. And then you can see that's it. In the Airbnb one, we had to add the robots.txt. In this one, we didn't. So everyone is gonna configure a little bit differently, but all you have to do is just read through the command, the arguments, and then the environment variables. And in this case, unlike the Airbnb one, we actually do need an API key. So what we're gonna do is we're gonna put in all caps BRAVE_API_KEY. So in the environment variables, I'm gonna change this to an expression just so we can actually see BRAVE_API_KEY. And then I'm gonna put an equals, and then it says to put your actual API key. So that's where we're gonna paste in the API key from Brave Search. Okay, so I put in my API key. Obviously I'm gonna remove that after this video gets uploaded, but now we'll hit save and we'll make sure that we're good to go. Cool. And now we're going to actually test this out. So I'm going to call this Brave Search Tools. And then before we add the actual execute tool, I'm just going to ask and make sure it works. So what Brave Search Tools do you have? And it knows, of course, to hit the Brave Search because we gave it a good name. And it should be pulling back with its different functions, which I believe there are two. Okay, so we have Brave Web Search and we have Brave Local Search. We also have, you know, of course, the description of when to use each one and the actual schemas to send over. So let's add a tool and make sure that it's working. We're going to click on the plus. We're going to add an MCP client tool. We already have our Brave credential connected. We're going to change the operation to execute tool. And once again, we're going to fill in the tool name and the parameters. So for the tool name, same exact thing. We're going to do from AI. And once again, this is just telling the AI what to fill in here. So we're going to call it tool. We're going to give it a very brief description of the tool selected. And then we are just going to enable the tool parameters to be filled out by the model automatically. Final thing is just to call this Brave Search execute. Cool. There we go. So now we have two functions for Airbnb, two for Brave Search, and let's make sure that the agent can actually distinguish between which one to use. So I'm going to say, search the web for information about AI agents. So we'll send that off. Looks like it's going straight to the Brave Search Execute. So we may have to get into the system prompt and tweak it a little bit. Now it's going back to the Brave Search Tools to understand, okay, what actions can I take? And now it's going back to the Brave Search Execute tool. And hopefully this time it'll get it right. So it looks like it's going to compile an answer right now based on its search result. And then we'll see exactly what happened. There we go. So we have, looks like, oh wow, it gave us 9 different articles. Um, what are AI agents by IBM? We can click into here to read more. So this takes us straight to IBM's article about AI agents. We have one also from AWS. We can click into there. There's Amazon. And let's go all the way to the bottom. We also have one on agents from Cloudflare. So let's click into here and we can see it took us exactly to the right place. So super cool. We didn't have to configure any sort of API documentation. As you can see in Brave Search, if we wanted to connect to this a different way, we would have had to copy this curl command. Statically set up the different headers and the parameters, but now with the server, we can just hit it right away. So let's take a look in the agent logs though, because we wanna see what happened. So the first time it tried to go straight to the execute tool, and as you can see, it filled in the parameters incorrectly, as well as the actual tool name, because it didn't have the information from the server. Then it realized, okay, I need to go here first so that I can find out what I can do. I tried to use a tool called web search, as you can see earlier, web search, but what I needed to do was use a tool called brave_websearch. So now on the second try, back to the tool, it got it right and it said brave_websearch. It also filled out some other information like how many articles are we looking for and what's the offset. So if we were to come back in here and say, get me one article on dogs, let's see what it would do. So hopefully it's gonna fill in the count as 1. Once again, it went straight to the tool and it may, I was gonna say, if we had memory in the agent, it probably would've worked. Because it would've seen that it used brave_websearch previously. But there's no memory here, so it did the exact same pattern. And we would basically just have to prompt in this agent, hey, search the MCP server to get the tools before you try to execute a tool. But now we can see it found one article. It's called, it's just Wikipedia. So we can click in here and see it's dog on Wikipedia. But if we click into the actual brave_search_execute tool, we can see that what it filled out for the query was dogs, and it also knew to make the count 1. Rather than last time it was 10. Okay, so something I want you guys to keep in mind is when you're connecting to different MCP servers, the setup will always be the same, where you'll look in the GitHub repository, you'll look at the command, which will be npx, you'll look at the arguments, which will be -y space the name of the server, and then sometimes there'll be more. And then after that, you'll do your environment variable, which is gonna be a credential, some sort of API key. So here, what we did was we asked Airtable to list its actions. And in this case, as you can see, it has 13 different actions. And within each action, there's going to be different parameters to send over. So when you start to scale up to some of these MCP servers that have more actions and more parameters, you're going to have to be a little more specific with your prompting. As you can see in this agent, there's no prompting going on. It's just your helpful assistant. And what I'm going to try is in my Airtable, I have a base called Contacts, a table called Leads, and then we have this one record. So let's try to ask it to get that record. Okay, so I'm asking it to get the records in my Airtable base called Contacts in my table called Leads. Okay, so we got the error received tool input did not match expected schema. And so this really is because what has to happen here is kind of complex. It has to first of all go get the bases to grab the base ID, and then it has to go grab the tables in that base to get the table ID, and then it has to formulate that over in a response over here. As you can see, if the operation was to list records, it has to fill out the base ID and the table ID in order to actually get those records back. So that's why it's having trouble with that. And so a great example of that is within my email agent for my Ultimate Assistant, in order to do something like label emails, we have to send over the message ID of the email that we wanna label, and we have to send over the ID of the label to actually add to that message. And in order to do those two things, we first have to get all emails to get the message ID, and then we have to get labels to get the label ID. So it's a multi-step process. and that's why this agent with minimal prompting and not a super robust parameter in here, it's literally just defining by the model. It's a little bit tough, but if I said something like, get my Airtable bases, we'll see if it can handle that because that's more of a one-step function. And it looks like it's having trouble because if we click into this actions, we can see that the operation of listing bases sends over an empty array. So it's having trouble being able to like send that data over. Okay, so I'm curious though, I went into my Airtable and I grabbed the base ID. Now I'm gonna ask what tables are in this Airtable base ID, and I gave it the base ID directly so it won't have to do that list bases function. And now we can see it actually is able to call the tool, hopefully. So it's green and it probably put in that base ID and we'll be able to see what it's doing here. But this just shows you there are still obviously some limitations and I'm hoping that n8n will make a native, you know, MCP server node. But look, what it was able to do now is it has Here are the tables within the Airtable base ID that we provided, and these are the 4 tables, and this is correct. And so now I'm asking it what records are in the Airtable base ID of this one and the table ID of this one, and it should be able to actually use its list records tool now in order to fill in those different parameters, and hopefully we can see our record back, which should be Robert California. So we got a successful tool execute, as you can see. Let's wait for this to pop back into the agent and then respond to us. So now we have our actual correct record. Robert California, Sabre, Custom AI Solution, all this kind of stuff. And as you can see, that's exactly what we're looking at within our actual Airtable base. And so I just thought that that would be important to show off here, how this is like really cool, but it's not fully there yet. So I definitely think it will get there, especially if we get some more native integrations with N8N. But I thought that that would be a good demo to show the way that it needs to fill in these parameters in order to get records. And you know, this type of example applies to Tons of different things that you'll do within MCP servers. So there's one more thing I wanna show you guys real quick, just so you will not be banging your head against the wall the way I was a couple days ago when I was trying to set up Perplexity. So because you have all these different servers to choose from, you may just trust that they're all gonna be the exact same and they're gonna work the same. So when I went to set up the Perplexity Ask MCP server, I was pretty excited. Command was npx, I put in my arguments, I put in my environment variable, which was my Perplexity API key. And you can see I set this up exactly as it should be. My API key's in there. I triple-checked to make sure it was correct. And then when I went to test step, basically what happened was couldn't connect to the MCP server, connection closed. And so after digging into what this meant, because I set up all these other ones, as you can see in here, I did these and I have more that I've connected to. The reason why this one isn't working, I imagine, is because on the server side of things, on Perplexity side of things, it's either going, undergoing maintenance or it's not fully published yet. And it's not anything wrong with the way that you are deploying it. So I just wanted to throw that out there because there may be some other ones in this big list that are not fully there yet. So if you are experiencing that error and you know that you're filling out that, you know, MPX and the arguments and the environment variable correct, then that's probably why. Don't spend all day on it. Just wanted to throw that out there because, you know, I had, I had a moment the other day. But that's going to be it for today's video. I hope you guys enjoyed it. Hope you learned something new. If this one helped out, please give it a like. It definitely helps me out a ton. And as always, appreciate you guys making it to the end of the video, and I will see you all in the next one. Thanks everyone.