MCP's New Spec Breaks Everything You Built — Here's What to Do | Du'An Lightfoot, Akamai

When we started building on MCB, it was yet another exciting shiny new thing and a shiny new standard. People were doing whatever they wanted to do. Then it was open-source and as we have seen with every other open-source project. Uh as the adoption goes grows, uh the usage grows, new users come in and they try to bring their own problems and they wanted to solve. So it quickly became the backbone that connects all AI systems to your tools and data. Now with growth of usage developers uh started to demand different things and they were starting to do different things. So the community they released the latest specifications for MCP uh which changed the way you we used to work uh whether it's uh sessions uh servers security everything has changed and it's good also because now you have stateful uh no more you know stateless things but it is a lot of changes so today we have with us Dan Lightoot senior developer advocate for AI engineer Akamay to not only unpack but to also talk about you know how it serves developers and we will talk a lot about the whole MCP space as well but before that first of all Dan it's great to have you on the show >> hey Swamnil thank you for having me today I'm glad to be here and hello everyone >> it's my pleasure so let's start with you know I mean of course it's not even a question that who doesn't know about MCP but let's just quickly talk about the role MCP since Enthropic announced it then it was open source but now it is playing it is plugging into it has kind of you know become a backbone. So talk about the role of MCPS before we talk about specification and what has changed. >> Yeah. So when you think about AI applications whether it's a coding agent or you have some other agent that are performing tasks what helps an agent be successful and actually play the role of an agent is the tools it has access to. And so those tools can come in the form of get you know with traditional connecting the traditional backend APIs to let's say get the weather get some information from a database or they can just come from looking up information on some other backend storage where you have some data right well in order to connect the tools traditionally what you would have what you would have to do as a developer was you would have to write let's say Python functions and you would have to write them connect it to your agent and then scale that to every agent that you have. So there was a lot of manual work in order to give capabilities to agents and AI applications. What MCP did was it said okay let's standardize a way to build tools and provide them to AI applications in this standardized way. Now when it was first released it was through standard in standard out. So everybody was building MCP servers and running them on their laptop or desktop. Well, in enterprise, you know, since it's standardized, it also needs to be centralized. So we needed HTTP streamable HTTP. So now we could host this on a virtual machine or Docker container and then other developers can connect to this MCP server, get the tools and capabilities, and it's constantly been progressing to where we are today. Now let's talk about this latest you know specifications what has changed and what kind of impact it will have on developers and the way they plug things to AI and LLMs. >> Yeah. So when you think when we were talking about the the initial version of MCP it had this client server relationship one client connect to a single MCP server right. So if you wanted to scale as a business to have an MCP server and scale it across multiple servers and multiple users, you would struggle with that because you couldn't put it behind a load balancer and do something like round robin. What this new version allows you to do is remove the session in the handshake that would happen with MCP, right? So now every request kind of stands alone, right? And any server, you know, can answer any request. So now you can actually do that round robbing when it comes to MCP behind a normal load balancer. This helps scale for an organization, you know, and it also increases reliability because now you're not also maintaining that session state on your end. This is more on the client side when it comes to managing MCP. There's also some tightening around securityurities improvements. There's introductions around interactive apps, right? So now you can send forms or send additional information or request did you really want to make this change through the MCP server, right? And then if you have long running tasks, you can create some type of ticketing to say, okay, this task is going to take maybe an hour. Send it back to the agent. The agent now can check back to see how long it's going to take. Um, one last thing which is also important when it comes to MCP is that before when changes happen, there was no real way to um, mitigate when these change happen within your application. Now, you get a one-year notice before anything is removed, right? So they kind of standardized to say hey we're delivering MCP to the community since it's open source and we're going to make sure that it's stable and um available for businesses to be able to use it within their enterprise applications. Interesting thing with standards is that there was a joke also know we love standards so much that we have made so many of those and that becomes a problem while you know on paper MCP does look like you know standardize but when it comes to day-to-day you know and also depends on the provider you're using the kind of tool you're using everybody is doing their own things those there is a kind of fragmentation also how you talk to those they are everybody is doing their own implementation how much fragmentation problem is there and will this because it is solving a lot of major problems that we face day-to-day. Will it push organizations towards more standardized uh standard or will that fragmentation remain? >> There will be fragmentation in the older version. The newer version was designed to operate more like traditional um APIs right through HTTP. So rather than you having that client server relationship, you know, you kind of just build your MCP server and then you connect to it like a traditional API, right? So I I believe that um there will may be some challenges around um the security and the risk around MCP but when it comes to being able to roll it out and use it and consume it I believe the changes that they have made have made it more in line with how you would um scale a um API within your organization. Now let's talk about some of the biggest things which is going to impact almost everybody which is statelessness you know uh talk a bit about uh what does removing protocol label sessions unlock for organizations running MCPS at a scale and how does that shift make changes to uh performance reliability deputability and most importantly security >> the the session ID has been removed from um the new version of MCP. So there's no more sticky routing, right? No more sessions stored by the server. You know, caching and tracing works like traditional APIs. Um but the one thing about that is that some of the risk has been removed, but it also didn't vanish because you don't have a session ID. There's no stealing of the um session or the state and being able to to replay it, right? Um the app [clears throat] memory now travels through the client. So anything that you want to remember and send back that needs to happen via okay I want to have a a connection to this MCP server. Well the MCP server may provide you like a a cookie like in a traditional application. And so when that cookie comes back the the um requester has to send that back to the server. And now the server needs to analyze this to ensure that it who that the cookie or the state wasn't altered, right? It belongs to the person that's asking and it hasn't expired. Now the protocol for the new MCP server does not tell us how to do that, but it says that this is something that you should do. Beyond statelessness, the newspec also enables richer interactions from multi- roundtrip request and longing task to MCP apps and broader extensions model. Uh talk a bit about because when we look at a you folks enable so many businesses uh real time I mean the use cases are just beyond comprehension. So talk a bit about what new possibilities will these unlock that developers, users, organizations, business were not able to do. Uh now we have to also consider security risk whether they will eliminate them or introduce new risks. >> All right. So when it comes to this new version of MCP tools can now pause and ask the user a question. So let's say you request to remove a file or change a file on a database or some other um storage location. the tool can pause and the server can request hey do you really want to do this and you can reply back that say yes I do want to do this and then when it comes to longunning tasks if a developer is working on an application and they have a a tool call for MCP server then that workload is going to take a longer time on the back end well the server can actually send a ticket or some ID number back to the AI application and the AI application can now drop that request and on the next request check the status of that long running task and for to me that really um that changes how we use AI right because now the work happens on the server rather than tying up the connection between something like cloud code or codeex and it's having that async communication right or that synchronous communication that's waiting it now can be more asynchronous we say hey okay this job is working we can check back later and move more now there the the one one more thing that I'll cover is that when it comes to apps which is a new feature interactive feature within MCP is that it could actually send maybe a form or some type of data within the um return from the server to the user which is interesting right um because now the backend can really send you know a request or some verification or some other type of app to the user through AI, right? Rather than the AI have having to render that, this can happen from the server. But there are some risks, right? Those ticket ids for those long running requests, they become targets, right? So when we think about that, well, how do you protect against that, right? The same with the cookies and the state and verifying has it been altered? Does it really belong to the user that done the request? Has it expired? There needs to be some controls on the server to do that verification. Now, another thing about those longunning tasks is that now this is an attack surface because those longunning tasks could be cheap to implement, cheap to start, but then they're costly to run, but also an attacker now could do a denial of service because now they're doing a bunch of requests in that application. So, that's something we got to think about as well. um when it comes to the app, if you're sending a form now, you got to worry about like prompt injection or fishing inside of that form when it comes back. So, those are some of the things that we have to think about when we're implementing or rolling out this new version of MCP and its features. >> We can put as many guard rails as we want. We can even put gates, but we all know there was a saying in Jurassic Park, life finds way, AI finds a way, you know, to break those. So, so hall el hall elucination is there making things up and then try to validate it or even try to remove the traces will there uh in these new specifications or from your perspective as AI is moving into production the kind of uh uh disclaimer that hey AI can make mistakes you know double check is not going to work because damage can be done and damage can be much more severe uh whether at standard level protocol level work. Either the work is already underway or should be done to kind of prevent as much possible hallucination or such risky behavior where it can actually uh we have seen cases where agents interact with each other to compromise the secrets you know or to get access because they have to get something done. So they will behave just like humans behave actually. Uh so talk a bit about uh are these guarders part of this specification or you feel that no that is something we must do but that is for future. Yeah. So when you think about using AI, right? MCP is a server, right? How do you protect the server? Well, the network layer is the first place to start, right? Um what should actually connect to your MCP server? I would start there, right? And then if you have like a load balancer, well, your load balancer can do protection at that layer 7, right? Checking the headers because now it acts like traditional HTTP. So the these are things we got to think about. So between your network layer with your firewalls, your access control list and then your layer 7 um load balancer or or W web application firewall. You can do some mitigation there. Um when it comes to guard, now you're thinking about the firewall around let's say the AI whether it's your AI agent or your LLMs, you could put guard rails to protect against those prompt injections. There's some W applications that do that as well that look inside of the payload. Um, but there are mitigations that we've been doing traditionally with HTTP and now we can actually do that with MCP since we don't actually have to go in that JSON body. We can actually just look at the headers now to really do some protections for our applications. >> Excellent. Uh, thank you for taking the question. Now, of course, everybody has already deployed MCP in production, MCP client servers. uh what should those setups what should those teams who have this very crazy very complicated very complex you know the whole MCP client server deployment uh what should they do what are the biggest migration or security uh things that they should be worried about >> yeah so when it comes to the m the the migration from traditional or the older version of MCP one of the things you got to think about is that I mentioned that when MCP was first rolled out you had a lot of standard in standard out So what did that mean? You had m developers spinning up MCP servers on a laptop all across your organization, right? You had teams spinning up MCP servers in different environments. Um so the the question is do you have let's say a load balancer web application firewall to monitor the traffic to see what MCP servers are out there because you can look at the headers and identify that. So identify what MCP servers are out there, right? find out where they are, look at the logs, look at the versions, and verify. Now, if you're trying to migrate, there's no real direct path from the older version. You know, this is a new implementation. So, you'll have to focus on that. Um, the second thing is that when you put the new version out, you know, the old handshakes from the clients are going to break, right? Because there's no there's no session ID, none of that exists. Um, the new version also doesn't have sampling, doesn't have roots. um logging in old CL client information. So those are some of the things that you have to think about. Um but I would start with just identifying what MCP servers you have that are out there. Now what are the features right? Um this is an opportunity to really design your MCP servers more efficiently. Um because one of the biggest challenges with MCP servers um from a few months ago, less than six months ago was token bloat. And now you know everyone's talking about tokconomics. This is an opportunity to figure out what tools do you actually need in your MCP servers? How are they actually designed? What does the um dock streams look like? Can you simplify this and make it more efficient in in your organization? If you just look at from purely developers point of view, how how is going to solve some of their problems, some of their struggles, some of their frustration when their day-to-day life has changed, they got access to the things they want, they got things the way they want and also security wise because it is actually you know every time you plug into you have to think about so many things and sometime you cannot even think about that. So talk about the the impact on developers day-to-day life who is totally hooked into MCP. >> Yeah, from a developer perspective, a lot of developers are using MCP servers. Um, they've built their own MCP servers depending on how deep they are in AI. When it comes to this migration, it's it's a question of okay, does this MC MCP server solve my needs? Right? If you have one in your organization and it connects to your application, well, now you're more if you're building AI agents that requests information, you can do a lot more, right? Long running tasks, forms, apps within MCP. This is an opportunity to figure out, okay, I've been wanting to build these specific workflows, but the problem that I was having was that I had this hangup with MCP. It was adding latency to my application. Well, now what you could actually do is rather than waiting on this job to finish, you could actually move on within your application, maybe decrease some latency, increase user experience. There's a lot of different things that you can do from a developer perspective. But I think because it's so new, it's going to take some experimenting and finding out what works, what doesn't work, and how to actually apply it at scale within your organization. As organizations make this transition, how can Akami help them migrate to the new MCP architecture more securely? >> I mentioned when you have a web application firewall and you have a load balancer and you have these different um network tools and resources within your organization. Often those that are watching this and they've heard of Akami and they're familiar with Akami, they're probably rug running it in their organization. So that means we're already protecting their API traffic. So since we're protecting your API traffic, this new version of MCP is in line with that, right? Because it's using HTTP. So now since we're already in front of that, we can put the the web application firewall and our tools in front of your MCP servers and then we can monitor those traffic, check the headers, right? help you with that mitigation from or that migration from the old version to the new version, identify that traffic and also protect you at that edge when it comes to u malicious attacks or you know that rate limiting and everything that you're used to when you use Akama >> and while Akama is there to help for those teams who are just starting to plan their migration what are the things that they should do at their end what kind of homework how they should prepare their infrastructure their tools their server for this migration. >> Yeah, I I mentioned this before, but when it comes to prep preparing your service, identify what what your workloads are, right? Um identify the tools, identify the workloads, identify the um rate limiting that you may need, identify, you know, how many tokens that are being sent from your MCP server. These are things that you can do to identify. But when it comes to your application, what's actually connected to it? What's being served? You know, how are you going to handle the the the the different types of flows that come through MCP, right? If you're doing a long running task, well, now you need to figure out how do you identify and verify that task when it comes back, right? That request and that check. So, these are some of the things that you have to think about when you're moving to the new version of MCP. What are other things that you wish should have made to this specification or that is on your own wish list for the next iteration of specifications? >> When it comes to wish list, I I see MCP as being um the future of maybe app integration, right? Since we have tools like Hermes agent, openclaw and they're using skills. But if I am an app developer, right, and I want to integrate with these agents, skills are one way to do that. But why are we downloading a file when you can just connect to this MCP server, right? So I would like to see in the future if there's if it's possible if it happens if there is maybe like a central repository of MCP server like an app store right where everybody that has which I believe they will an agent on their phone can go to the app store download whatever MCP server or connect to that MCP server get the data get the tools that they need so we can all you know be build new things and be more efficient not just in the enterprise but in life. >> John, thank you so much for walking us through these changes and help our viewers kind of make sense of what all of that means from the perspective of course performance, productivity, but also security. So, thank you for that. And of course, those who are watching, please head over and check.com their blog post to learn more about these changes, the whole MCP evolution. And Dan, thank you so much for your time today and I look forward to chat with you again. Thank you. Thank you for having me.